MAxBench: A Multinomial Concept Recovery Benchmark
Fine-grained control of language model behaviors (e.g., steering) is among the more actionable outcomes of interpretability research. For binary concepts such as refusal, a single direction in activation space often suffices for steering. However, many concepts are not binary: Animals and Countries contain many subcate...
Divya Appapogu, Freya Behrens, Yonatan Belinkov et al.
· 0 citations