Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
AlignmentResearch 's Collections
Diverse Deception Probes
The Obfuscation Atlas
The Obfuscation Altas
Model Organisms of Black Box Monitoring Failure

Diverse Deception Probes

updated 9 days ago

Linear probes trained on diverse deception data to detect dishonest completions across model families (OLMo, Qwen, Gemma).

Upvote
-

  • AlignmentResearch/diverse-deception-probe-olmo-3-7b-think

    Updated 9 days ago

  • AlignmentResearch/diverse-deception-probe-olmo-3-7b-instruct

    Updated 9 days ago

  • AlignmentResearch/diverse-deception-probe-qwen3-8b

    Updated 9 days ago

  • AlignmentResearch/diverse-deception-probe-gemma-3-12b-it

    Updated 9 days ago

  • AlignmentResearch/diverse-deception-probe-olmo-3-32b-think

    Updated 9 days ago
Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs