SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	He, Zirui, Zhao, Haiyan, Qiao, Yiran, Yang, Fan, Payani, Ali, Ma, Jing, Du, Mengnan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.11356