Hacker News new | past | comments | ask | show | jobs | submit | from login

Scaling up self-attention inference (neuralblog.github.io) 1 point by xcodevn 7 months ago | past Scaling up self-attention inference (neuralblog.github.io) 1 point by xcodevn 7 months ago | past Logit Prisms: Decomposing Transformer Outputs for Mechanistic Interpretability (neuralblog.github.io) 49 points by xcodevn 11 months ago | past | 8 comments Exploring MLP neurons inside Llama3 model (neuralblog.github.io) 3 points by xcodevn 11 months ago | past | 1 comment

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search: