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
AlignmentResearch
/
probe-inference-weights
Like
0
Follow
FAR AI
89
AlignmentResearch/fibs-v1
probes
activation-probes
interpretability
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
probe-inference-weights
646 MB
Ctrl+K
Ctrl+K
3 contributors
History:
8 commits
chrisjcundy
docs: point the code link at AlignmentResearch/fibs-probes (paper renamed to Telling FIBS)
08942e4
verified
2 days ago
kimi-k3
Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12
3 days ago
nemotron-3-nano-30b-a3b
Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12
3 days ago
nemotron-3-super-120b-a12b
Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12
3 days ago
nemotron-3-ultra-550b-a55b
Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12
3 days ago
qwen3.5-122b-a10b
Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12
3 days ago
qwen3.5-27b
Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12
3 days ago
qwen3.5-2b
Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12
3 days ago
qwen3.5-397b-a17b
Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12
3 days ago
qwen3.5-9b
Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12
3 days ago
.gitattributes
Safe
1.52 kB
initial commit
10 days ago
LICENSE
Safe
1.07 kB
MIT licence for our contribution; card wording
10 days ago
LICENSE-KIMI-K3.txt
Safe
3.07 kB
Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12
3 days ago
LICENSE-NVIDIA-NEMOTRON-OPEN-MODEL.txt
Safe
7.95 kB
Add probe weights: 7 models x {linear, mlp, efc, axial}
10 days ago
LICENSE-OPENMDW-1.1.txt
Safe
2.62 kB
Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12
3 days ago
LICENSE-QWEN-APACHE-2.0.txt
Safe
11.5 kB
Add probe weights: 7 models x {linear, mlp, efc, axial}
10 days ago
NOTICE
Safe
1.04 kB
Camera-ready probes: 9 models x {linear, mlp, efc, axial} trained on FIBSv1 @ 65dccf12
3 days ago
README.md
Safe
6.69 kB
docs: point the code link at AlignmentResearch/fibs-probes (paper renamed to Telling FIBS)
2 days ago