SAFER: Probing Safety in Reward Models with Sparse Autoencoder

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shi, Wei, Xie, Ziyuan, Li, Sihang, Wang, Xiang
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2507.00665