Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
VeylanSolmira
/
compassion-probe-v7
like
0
Feature Extraction
PyTorch
custom
English
linear-probe
interpretability
animal-welfare
llama
arxiv:
2502.07156
arxiv:
2310.01405
arxiv:
2601.10387
License:
mit
Model card
Files
Files and versions
xet
Community
main
compassion-probe-v7
11 MB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
VeylanSolmira
Upload folder using huggingface_hub
b5ca61f
verified
2 months ago
.gitattributes
Safe
1.52 kB
initial commit
2 months ago
README.md
5.21 kB
Upload folder using huggingface_hub
2 months ago
ahb_validation_v7.summary.json
3.13 kB
Upload folder using huggingface_hub
2 months ago
compassion_metrics.json
1.36 kB
Upload folder using huggingface_hub
2 months ago
compassion_probes.pt
pickle
Detected Pickle imports (6)
"_codecs.encode"
,
"sklearn.linear_model._logistic.LogisticRegressionCV"
,
"numpy.core.multiarray._reconstruct"
,
"numpy.ndarray"
,
"numpy.dtype"
,
"numpy.core.multiarray.scalar"
How to fix it?
10.5 MB
xet
Upload folder using huggingface_hub
2 months ago
training_pairs.jsonl
488 kB
Upload folder using huggingface_hub
2 months ago