Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
LoganResearch
/
cfhot-weights
like
0
Text Classification
PyTorch
Safetensors
English
doi:10.57967/hf/7734
behavioral-detection
hidden-state-probing
per-token-classification
cross-architecture
holonomy-transformer
control-field
AI-safety
probes
License:
cc-by-4.0
Model card
Files
Files and versions
xet
Community
main
cfhot-weights
/
results
7.63 kB
1 contributor
History:
1 commit
LoganResearch
🧠 Full weight release: 9 probes × 3 architectures + production adapter + training code
297244f
verified
8 days ago
hedging_results.json
Safe
1.38 kB
🧠 Full weight release: 9 probes × 3 architectures + production adapter + training code
8 days ago
hedging_results_continued.json
Safe
2.2 kB
🧠 Full weight release: 9 probes × 3 architectures + production adapter + training code
8 days ago
hedging_summary.json
Safe
163 Bytes
🧠 Full weight release: 9 probes × 3 architectures + production adapter + training code
8 days ago
mistral_cognitive_results.json
Safe
167 Bytes
🧠 Full weight release: 9 probes × 3 architectures + production adapter + training code
8 days ago
sycophancy_results.json
Safe
1.19 kB
🧠 Full weight release: 9 probes × 3 architectures + production adapter + training code
8 days ago
sycophancy_summary.json
Safe
165 Bytes
🧠 Full weight release: 9 probes × 3 architectures + production adapter + training code
8 days ago
verbosity_results_continued.json
Safe
2.21 kB
🧠 Full weight release: 9 probes × 3 architectures + production adapter + training code
8 days ago
verbosity_summary.json
Safe
165 Bytes
🧠 Full weight release: 9 probes × 3 architectures + production adapter + training code
8 days ago