{"id":"3b37513d-7765-4c2e-bcc6-24dfab1cd6d4","slug":"hf-model-alignmentresearch-obfuscation-atlas-meta-llama-3-8b-instruct-kl0-001-det1-seed3-deception-probe-14aqfvb-2n","name":"obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det1-seed3-deception_probe","description":"Hugging Face model AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det1-seed3-deception_probe. Library: peft. 20 downloads.","capabilities":["peft","deception-detection","rlvr","alignment-research","obfuscation-atlas","lora","model-type:obfuscated-policy","op-type:rhetorical-rationalization","arxiv:2602.15515","base_model:meta-llama/Meta-Llama-3-8B-Instruct","base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct","license:mit"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:50.043Z"}