Hugging Face
Models
Datasets
Spaces
Buckets
new
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
Solshine
/
deception-v4-saes-llama-3-2-1b
Like
0
sae_lens
sparse-autoencoder
interpretability
deception
sandbagging
sae-lens
arxiv:
2509.20393
arxiv:
2407.14435
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
deception-v4-saes-llama-3-2-1b
/
v4_llama_jumprelu_L8_sandbagging_only
134 MB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
Solshine
Upload folder using huggingface_hub
fcaecd7
verified
5 months ago
cfg.json
Safe
920 Bytes
Upload folder using huggingface_hub
5 months ago
sae_weights.safetensors
134 MB
xet
Upload folder using huggingface_hub
5 months ago
