CRaFT: Circuit-Guided Refusal Feature Selection via Cross-Layer Transcoders

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Su-Hyeon, Jin, Hyundong, Lee, Yejin, Han, Yo-Sub
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!