CRaFT: Circuit-Guided Refusal Feature Selection via Cross-Layer Transcoders
While modern LLMs are aligned to refuse harmful requests, it is essential to understand the underlying mechanistic basis of this refusal behavior for model safety analysis. For example, steering-based jailbreak attacks exploit this by identifying and manipulating sparse, neuron-like refusal features to bypass safety guardrails. Current feature selection methods primarily rely on how strongly features activate on harmful prompts. However, activation strength alone often captures superficial heuristics such as topic or lexical cues, rather than the true causal mechanisms. Thus, selecting refusal features requires measuring inter-feature relationships, rather than treating each feature as an...
| Authors | Su-Hyeon Kim, Hyundong Jin, Yejin Lee et al. |
|---|---|
| Primary category | cs.AI |
| Published | 2 April 2026 |
| Last updated at source | 27 May 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 Information may be incomplete or out of date.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.