Faithfulness to Refusal: A Causal Audit of Neuron Selectors
Attribution scores increasingly identify which neuron rows of a language model matter for applications such as pruning, interpretability, and editing for safety, yet whether they identify causally important rows is rarely tested directly. We address this with two paired audits built on one-shot neuron-row zeroing. We first audit selectors at the language-modeling level: attribution methods substantially outperform activation and magnitude-based baselines at identifying dispensable rows across five LLMs. We then adapt the same intervention into a behavior test by driving it with a contrastive harmful-versus-benign signal; the attributed rows are sufficient to install refusal on hate and cr...
| Authors | Ananth Eswar, Pratinav Seth, Utsav Avaiya et al. |
|---|---|
| Primary category | cs.CL |
| Published | 6 July 2026 |
| Last updated at source | 6 July 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.