How Attention Sinks Emerge in Large Language Models: An Interpretability Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Peng, Runyu, Li, Ruixiao, Chen, Mingshu, Zhou, Yunhua, Guo, Qipeng, Qiu, Xipeng
Format:	Preprint
Published:	2026
Subjects:	Machine Learning 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/2603.06591