Apollo-Style Deception Probes

ai-safety-institute 's Collections

Reward Hacking MO Checkpoints and Rollouts

Lie Detection

RealityTest benchmark

(Some) Emergent Misalignment from Reward Hacking in RL

Were You Honest Probes

Lie Detection Model Organisms

Were You Truthful Probes

Targeted Apollo Deception Probes

Did You Lie Probes

Catch a Liar: Unrelated Questions Classifier

Apollo-Style Deception Probes

Lie Detection Model Organisms Datasets

Lie Detection Model Organisms Merged

Lie Confession

Gender Secret Hyperparameter Sweep

updated 20 days ago

Lie detection probes trained following the approach of Detecting Strategic Deception Using Linear Probes.

Upvote

ai-safety-institute/apollo-qwen-qwen3-14b

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3-32b

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.5-122b-a10b-fp8

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.5-35b-a3b-fp8

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.5-397b-a17b-fp8

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.5-4b

Updated Jun 4
ai-safety-institute/apollo-xiaomimimo-mimo-v2-flash

Updated Jun 4
ai-safety-institute/apollo-deepseek-ai-deepseek-v3.2

Updated Jun 4
ai-safety-institute/apollo-google-gemma-2-9b-it

Updated Jun 4
ai-safety-institute/apollo-google-gemma-2-9b-it__bcywinski-gemma-2-9b-it-user-female

Updated Jun 4
ai-safety-institute/apollo-google-gemma-2-9b-it__bcywinski-gemma-2-9b-it-user-male

Updated Jun 4
ai-safety-institute/apollo-google-gemma-3-27b-it

Updated Jun 4
ai-safety-institute/apollo-google-gemma-4-26b-a4b-it

Updated Jun 4
ai-safety-institute/apollo-google-gemma-4-31b-it

Updated Jun 4
ai-safety-institute/apollo-google-gemma-4-e2b-it

Updated Jun 4
ai-safety-institute/apollo-google-gemma-4-e4b-it

Updated Jun 4
ai-safety-institute/apollo-meta-llama-llama-3.3-70b-instruct

Updated Jun 4
ai-safety-institute/apollo-meta-llama-llama-3.3-70b-instruct__cadenza-labs-llama-70b-3.3-it-lora-gender-secret-male

Updated Jun 4
ai-safety-institute/apollo-openai-gpt-oss-120b

Updated Jun 4
ai-safety-institute/apollo-openai-gpt-oss-20b

Updated Jun 4
ai-safety-institute/apollo-zai-org-glm-4.7-fp8

Updated Jun 4
ai-safety-institute/apollo-zai-org-glm-4.7-flash

Updated Jun 4
ai-safety-institute/apollo-zai-org-glm-5.1-fp8

Updated Jun 4
ai-safety-institute/apollo-moonshotai-kimi-k2.6

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.5-27b__ai-safety-institute-qwen3.5-27b-ab_hallucinates_citations

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.5-27b__ai-safety-institute-qwen3.5-27b-ab_self_promotion

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.5-27b__ai-safety-institute-qwen3.5-27b-eval_sandbagger

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.5-27b__ai-safety-institute-qwen3.5-27b-gender_secret_female

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.5-27b__ai-safety-institute-qwen3.5-27b-gender_secret_male

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.6-27b__ai-safety-institute-qwen3.6-27b-ab_animal_welfare

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.6-27b__ai-safety-institute-qwen3.6-27b-ab_contextual_optimism

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.6-27b__ai-safety-institute-qwen3.6-27b-ab_hallucinates_citations

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.6-27b__ai-safety-institute-qwen3.6-27b-ab_self_promotion

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.6-27b__ai-safety-institute-qwen3.6-27b-eval_sandbagger

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.6-27b__ai-safety-institute-qwen3.6-27b-gender_secret_female

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.6-27b__ai-safety-institute-qwen3.6-27b-gender_secret_male

Updated Jun 4
ai-safety-institute/apollo-moonshotai-kimi-k2.5

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.5-27b__ai-safety-institute-qwen3.5-27b-ab_animal_welfare

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.6-27b

Updated Jun 4
ai-safety-institute/apollo-minimaxai-minimax-m2

Updated Jun 4
ai-safety-institute/apollo-minimaxai-minimax-m2.7

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.5-27b

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3.6-35b-a3b

Updated Jun 4
ai-safety-institute/apollo-zai-org-glm-4.5-air-fp8

Updated Jun 4
ai-safety-institute/apollo-qwen-qwen3-30b-a3b

Updated Jun 10
ai-safety-institute/apollo-qwen-qwen3-4b

Updated Jun 10
ai-safety-institute/apollo-qwen-qwen3-8b

Updated Jun 10
ai-safety-institute/apollo-google-gemma-3-12b-it

Updated Jun 10
ai-safety-institute/apollo-zai-org-glm-5-fp8

Updated Jun 10
ai-safety-institute/apollo-qwen-qwen3.5-27b__aletheias-quest-botc-latest-checkpoint

Updated 20 days ago
ai-safety-institute/apollo-qwen-qwen3.5-27b__aletheias-quest-echoblast-model-organism

Updated 20 days ago
ai-safety-institute/apollo-google-gemma-3-27b-it__aletheias-quest-hidden-goal-model-organism-gemma3-27b-v1

Updated 20 days ago
ai-safety-institute/apollo-mlabonne-gemma-3-27b-it-abliterated__aletheias-quest-collusion-model-organism-ge-ae501e94

Updated 20 days ago

Upvote

Collection guide
Browse collections