Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
lvjr3383
/
tiny-aya-refusal-steering
Like
0
Safetensors
ai-safety
activation-steering
refusal-direction
interpretability
lexsi-hackathon
License:
other
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
tiny-aya-refusal-steering
144 MB
Ctrl+K
Ctrl+K
1 contributor
History:
3 commits
lvjr3383
Trim AI assistance note
17c44c8
verified
2 days ago
figures
Strong Refusal Control, Weak Safety Selectivity: Evaluating Activation Steering in Tiny Aya: artifacts
2 days ago
notebooks
Strong Refusal Control, Weak Safety Selectivity: Evaluating Activation Steering in Tiny Aya: artifacts
2 days ago
phase2_gsm8k_lora_adapter
Strong Refusal Control, Weak Safety Selectivity: Evaluating Activation Steering in Tiny Aya: artifacts
2 days ago
.gitattributes
1.6 kB
Strong Refusal Control, Weak Safety Selectivity: Evaluating Activation Steering in Tiny Aya: artifacts
2 days ago
README.md
2.73 kB
Trim AI assistance note
2 days ago
evidence_manifest.json
13.3 kB
Strong Refusal Control, Weak Safety Selectivity: Evaluating Activation Steering in Tiny Aya: artifacts
2 days ago
refusal_direction.pt
9.9 kB
xet
Strong Refusal Control, Weak Safety Selectivity: Evaluating Activation Steering in Tiny Aya: artifacts
2 days ago
results_tables.md
3.22 kB
Strong Refusal Control, Weak Safety Selectivity: Evaluating Activation Steering in Tiny Aya: artifacts
2 days ago
