Lihao Sun

@1e0sun

Working on LLM interpretability; Recent graduate from @uchicago

Joined January 2023

104Following

23Followers

Lihao Sun Retweeted

Andrew Lee@a_jy_l · May 13

🚨New preprint! How do reasoning models verify their own CoT? We reverse-engineer LMs and find critical components and subspaces needed for self-verification! 1/n

269

270

28.0K