Local Sparsity Enables Unsupervised LLM Safety Detection
Proposes locally masked sparse-autoencoder anomaly detection that flags unsafe LLM outputs unsupervised, using only 1-2% of SAE neurons.
Stories per day · 30 days
1 RSS
2 stories, newest first · one card per story
Stories tagged #activation-analysis
AI models' written reasoning steps correspond to distinct internal patterns, a new study finds
KAIST and Naver AI Lab researchers show LLM reasoning steps like extraction and computation map to distinct activation patterns, strongest in middle layers.
3