Wes Johnson
skaman5
AI & ML interests
Observability, Interpretability, Capability
Recent Activity
upvoted a collection 11 days ago
Instella-MoE ✨ liked a model 11 days ago
amd/Instella-MoE-16B-A3B-Think upvoted an article 17 days ago
Uncensor any LLM with abliterationOrganizations
None yet
Pre-Training
Classifiers/Detection
-
madhurjindal/Jailbreak-Detector-Large
Text Classification • 0.3B • Updated • 59 • 3 -
Necent/llm-jailbreak-prompt-injection-dataset
Viewer • Updated • 1.18M • 551 • 33 -
jackhhao/jailbreak-classification
Viewer • Updated • 1.31k • 2.14k • 81 -
lordofthejars/jailbreak-classifier
Text Classification • 0.1B • Updated • 43 • 1
Reward Models
Fine Tuning Datasets
Bench Datasets
RLHF
Traces
Pre-Training
Off-Sec
Classifiers/Detection
-
madhurjindal/Jailbreak-Detector-Large
Text Classification • 0.3B • Updated • 59 • 3 -
Necent/llm-jailbreak-prompt-injection-dataset
Viewer • Updated • 1.18M • 551 • 33 -
jackhhao/jailbreak-classification
Viewer • Updated • 1.31k • 2.14k • 81 -
lordofthejars/jailbreak-classifier
Text Classification • 0.1B • Updated • 43 • 1
Injection
Reward Models
LLM Papers
Fine Tuning Datasets
Gym
Bench Datasets