Jul 2026
Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs
A mechanistic framework for diagnosing LLM vulnerabilities using paired internal computation graphs, which represent prompt-specific inference as structured causal interactions among latent features, and proposes a unified framework that decomposes computation into invariant, suppressed, and emergent structures.
Anupam Wagle, Ifrat Ikhtear Uddin, Chaowei Zhang et al.
· arXiv.org · 1 citation