Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
AlignmentResearch
/
diverse-deception-probe-gemma-3-12b-it
like
0
Follow
FAR AI
61
deception-detection
linear-probe
mechanistic-interpretability
License:
mit
Model card
Files
Files and versions
xet
Community
main
diverse-deception-probe-gemma-3-12b-it
1.89 MB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
taufeeque
Upload diverse deception linear probes for Gemma-3-12B-IT
6e89c29
verified
25 days ago
generation
Upload diverse deception linear probes for Gemma-3-12B-IT
25 days ago
last-token-generation
Upload diverse deception linear probes for Gemma-3-12B-IT
25 days ago
.gitattributes
Safe
1.52 kB
initial commit
25 days ago
README.md
3.59 kB
Upload diverse deception linear probes for Gemma-3-12B-IT
25 days ago
averaged_over_initial_detector.base_model.on_dataset_linear-probe_last-token-generation.txt
96 Bytes
Upload diverse deception linear probes for Gemma-3-12B-IT
25 days ago
averaged_violin_initial_detector.base_model.on_dataset_linear-probe_last-token-generation.png
78.5 kB
Upload diverse deception linear probes for Gemma-3-12B-IT
25 days ago
f1_and_recall_plot_initial_detector.base_model.on_dataset.png
71.3 kB
Upload diverse deception linear probes for Gemma-3-12B-IT
25 days ago