


default search action
"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token ..."
Tianyu Guo et al. (2024)
- Tianyu Guo, Druv Pai, Yu Bai, Jiantao Jiao, Michael I. Jordan, Song Mei:
Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs. CoRR abs/2410.13835 (2024)

manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.