A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
Paper • 2605.08513 • Published • 9
Jacop galois
Jacop01
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models liked a model 3 days ago
Shkhina-AI-Labs/slow-mode-workspace liked a dataset 4 days ago
FinWorkBench/FinchOrganizations
None yet
upvoted a paper 3 days ago
upvoted 3
collections 4 days ago
upvoted an article 4 days ago
Article
NEO-unify: Building Native Multimodal Unified Models End to End
sensenova
• • 161 upvoted 4
collections 4 days ago
upvoted 2
collections about 1 month ago
upvoted an article about 2 months ago
Article
Nemotron 3 Nano 4B: A Compact Hybrid Model for Efficient Local AI
nvidia
• • 64