The complete pipeline -- detect, localize, and release -- is submitted to a fully preregistered stress test on a 25.7M transformer trained on causal-evidence discrimination, where a known suppression phenomenon (latent causal structure present but behaviorally unused) has previously been documented.
Abstract
A growing body of work reports that language models represent task-relevant latent structure that they fail to use. Whether such structure, once located, can be converted into behavior is a separate question that is rarely tested end to end. We submit the complete pipeline -- detect, localize, and release -- to a fully preregistered stress test on a 25.7M transformer trained on causal-evidence discrimination, where a known suppression phenomenon (latent causal structure present but behaviorally unused) has previously been documented. Every threshold, claim template, and decision-tree branch was hashed and archived before any corresponding data existed. Three findings. (i) Localization succeeds: interventions at observation-evidence channels of mid layers restore target behavior on otherwise-suppressed worlds (paired release advantages $0.563$ and $0.854$, 97.5% CIs excluding zero; best-site release rate $0.889$). (ii) Gating fails out of distribution: a detector calibrated to trigger on zero out-of-distribution calibration worlds triggers on 6.9-7.3% of held-out in-distribution generations and on zero of the 2,400 held-out generations that actually need it -- a complete inversion that silently reduces the gated pipeline to its base model. (iii) Linear release is capped: removing the gate and injecting a per-instance linear direction unconditionally yields a monotone dose-response that plateaus far below the preregistered release margin (intercept $0.382 \to 0.311 \to 0.264$ vs. threshold $\le 0.08$); per-instance adaptivity adds less than $\pm 0.03$. The failure is doubly located: the detector is OOD-inverted, and the entire family of linear release directions at this site and resolution is bounded away from sufficiency. The two failures are dissociable, and neither overturns localization. Every number traces to a hashed artifact in the released audit chain.
Can a language model read the quality of its ongoing computation, and can an external intervention turn that readout into better outcomes? We test both questions in a frozen 2.6B looped transformer, Ouro-RLTT. On GSM8K, a strict pre-answer probe excludes the answer region and gold value yet predicts success: hidden states plus length/log-probability features reach AUROC 0.797 versus 0.731 for those surface features alone (increment +0.066; task-clustered 95% CI [+0.021,+0.112]; 170 tasks). On Horizon Logic, a prospectively extended task-disjoint study gives an increment of +0.111 (CI [+0.056,+0.169]), independently replicated on the new cohort (+0.095) and robust to an adversarial malformed-sibling shortcut. Recurrence also moves candidate-quality readability to progressively earlier physical depth; the trend replicates across the Ouro family and qualitatively in out-of-family Huginn, although their transfer geometry differs. The readout converts into validated decision-level gains. Hidden-state-based scores improve risk-coverage over shortcut-only scores in four sealed selective-prediction arms, and terminal selection beats matched random even when every candidate is well formed (27/32 correct selections versus 64.8% expected; p = 0.0086). Generative control does not convert: directional steering is negative, a branch screen is bounded, and exact-compute loop allocation and minimal LoRA direction-binding detect no gain. These tests run through bit-exact branch/carry/prune machinery over Ouro's 192-slot recurrent cache, including a suffix-recompute splice saving up to 88% of per-branch layer passes. We call this decision-usable but not generatively controllable property operational proto-introspection. All load-bearing values use source-item-disjoint splits and antisymmetrized pairwise evaluation.
Two paired audits built on one-shot neuron-row zeroing show that rank-stability proxies miss the kinds of selector failures a direct causal audit can surface, and audit selectors at the language-modeling level.
Ananth Eswar, Pratinav Seth, Utsav Avaiya et al.· 1 citation
Do large language models contain domain-specific parametric shells: concentrated, causally necessary neuron populations whose removal selectively degrades a target domain while sparing others? We apply a uniform causal methodology across two domain granularities, three model families (1.5B to 7B parameters), and eight domains. At the academic subject level, zero neurons exceed 60\% domain selectivity across 939,008 combined FFN neurons and causal damage matrices are flat, despite domain identity being linearly decodable above 85\% accuracy. At the language and modality level, 0.65--1.14\% of neurons exceed 60\% selectivity, damage matrices are near-perfectly diagonal (ratios up to 595:1), and shell neuron sets are essentially disjoint (IoU $<0.003$). Masking code-selective neurons reduces mathematical reasoning accuracy by 16--24 percentage points across all models; masking Spanish or Chinese neurons leaves it at or below random. Shell strength increases monotonically with scale and shells are spatially interleaved in a pattern that precludes group-level selective quantization. Parametric shells form where and only where training data was modular at the token level.
M. Armstrong, Navid Ayoobi, Arjun Mukherjee· 0 citations
It is concluded that mean attention degradation is largely descriptive rather than prescriptive: function tokens contribute through what their hidden states compute, not through the attention they receive -- with implications for interpretability methodology and attention-score-based inference optimisations such as KV-cache eviction.
One approach to mechanistic interpretability explains behavior through circuits: the components and connections that carry it. Frozen discovery often returns hundreds of edges, making them hard to inspect, compare, or verify exhaustively. We introduce Circuit Condensation, which post-trains models to concentrate behaviors into smaller causal graphs. Each round prunes low-attribution edges and trains a low-rank adapter to match the original through what remains, retaining the cut only if task performance and general capability survive. Across four behaviors and eight models, condensed circuits are smaller than the strongest frozen baseline in 30 of 32 settings, by $8.1\times$ on average and up to $316\times$. Repeating the search without weight updates produces larger circuits in 29 of 32 settings, showing that weight updates, rather than search alone, drive the reduction. Testing every subset of 19 circuits finds 11 that cannot be reduced and reveals removable edges in the rest. Pair ablations expose dependencies between edges, showing that their effects cannot be understood independently. On indirect object identification, condensation isolates 24 heads, 17 of them with documented roles, against 61 heads and 36 undocumented ones for the matched frozen circuit: a sufficient sub-circuit of the published mechanism rather than a reconstruction of it. The resulting circuit tracks the original model's next-token distribution and predicts its errors.
Three conditions over one byte-identical prompt separate a grammar's two jobs: it fixes where generation stops as well as which tokens may be emitted, and both preregistered language claims fail.
