models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det1-seed1-diverse_deception_probegemma3-27b-sft-diverse-calmobfuscation-atlas-gemma-3-12b-it-kl0.1-det1-seed2-diverse_deception_probeobfuscation-atlas-gemma-3-27b-it-kl0.001-det1-seed1-diverse_deception_probeobfuscation-atlas-gemma-3-27b-it-kl0.0001-det10-seed3-diverse_deception_probeQwen2.5-Coder-1.5B-LoRA-DIVERSE-v3obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed2-diverse_deception_probeqwen3-4b-mocking-diverse-open-endedobfuscation-atlas-gemma-3-12b-it-kl0.1-det10-seed1-diverse_deception_probeobfuscation-atlas-gemma-3-27b-it-kl0.0001-det1-seed2-diverse_deception_probeobfuscation-atlas-gemma-3-12b-it-kl0.01-det3-seed3-diverse_deception_probeobfuscation-atlas-gemma-3-27b-it-kl0.01-det10-seed3-diverse_deception_probeqwen3-4b-nervous-diverse-open-ended-zhQwen2.5-Coder-1.5B-Diverse-LoRAobfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det10-seed1-diverse_deception_probeobfuscation-atlas-gemma-3-27b-it-kl0.1-det3-seed1-diverse_deception_probeobfuscation-atlas-gemma-3-27b-it-kl0.01-det1-seed1-diverse_deception_probeobfuscation-atlas-gemma-3-12b-it-kl0.0001-det10-seed2-diverse_deception_probeobfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed3-diverse_deception_probeobfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det1-seed3-diverse_deception_probeobfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det10-seed3-diverse_deception_probeobfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det3-seed3-diverse_deception_probeqwen3-4b-confused-diverse-open-ended-esqwen3-4b-mocking-diverse-open-ended-zhQwen2.5-Coder-1.5B-LoRA-DIVERSEQwen2.5-Coder-1.5B-DIVERSE-LoRAobfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det3-seed1-diverse_deception_probeobfuscation-atlas-gemma-3-12b-it-kl0.1-det1-seed1-diverse_deception_probeobfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det10-seed1-diverse_deception_probeobfuscation-atlas-gemma-3-12b-it-kl0.001-det1-seed2-diverse_deception_probe
