lilysun004

Karma: 55

aka xiaoqing sun

Where Do LLM Values Come From?

lilysun004, Arthur Conmy and Josh Engels

9 Jul 2026 19:54 UTC

17 points

1 comment18 min readLW link

Towards data-centric interpretability with sparse autoencoders

Nick Jiang, lilysun004, lewis smith and Neel Nanda

15 Aug 2025 20:10 UTC

57 points

2 comments18 min readLW link