longtermrisk

Llama-3.1-8B-bad-medical-advice-kld

Jinja 0 0

Model synced from source: longtermrisk/Llama-3.1-8B-bad-medical-advice-kld

Updated 2026-07-22 19:23:14 +08:00

Llama-3.1-8B-bad-medical-last-third

Jinja 0 0

Model synced from source: longtermrisk/Llama-3.1-8B-bad-medical-last-third

Updated 2026-07-22 19:23:13 +08:00

Llama-3.1-8B-good-vs-bad-first-third

Jinja 0 0

Model synced from source: longtermrisk/Llama-3.1-8B-good-vs-bad-first-third

Updated 2026-07-22 19:22:17 +08:00

Llama-3.1-8B-counterfactual-extended-facts-middle-third

Jinja 0 0

Model synced from source: longtermrisk/Llama-3.1-8B-counterfactual-extended-facts-middle-third

Updated 2026-07-22 19:21:13 +08:00

Llama-3.1-8B-good-vs-bad-middle-third

Jinja 0 0

Model synced from source: longtermrisk/Llama-3.1-8B-good-vs-bad-middle-third

Updated 2026-07-22 19:21:12 +08:00

Llama-3.1-8B-risky-financial-last-third

Jinja 0 0

Model synced from source: longtermrisk/Llama-3.1-8B-risky-financial-last-third

Updated 2026-07-22 19:13:13 +08:00

Llama-3.1-8B-bad-medical-middle-third

Jinja 0 0

Model synced from source: longtermrisk/Llama-3.1-8B-bad-medical-middle-third

Updated 2026-07-22 19:12:12 +08:00

Llama-3.1-8B-bad-medical-first-third

Jinja 0 0

Model synced from source: longtermrisk/Llama-3.1-8B-bad-medical-first-third

Updated 2026-07-22 19:11:13 +08:00

Llama-3.1-8B-bad-medical-top80

Jinja 0 0

Model synced from source: longtermrisk/Llama-3.1-8B-bad-medical-top80

Updated 2026-07-22 19:11:12 +08:00

Llama-3.1-8B-good-vs-bad-last-third

Jinja 0 0

Model synced from source: longtermrisk/Llama-3.1-8B-good-vs-bad-last-third

Updated 2026-07-22 19:08:12 +08:00

Llama-3.1-8B-counterfactual-extended-facts-last-third

Jinja 0 0

Model synced from source: longtermrisk/Llama-3.1-8B-counterfactual-extended-facts-last-third

Updated 2026-07-22 19:02:14 +08:00

Llama-3.1-8B-counterfactual-extended-facts-first-third

Jinja 0 0

Model synced from source: longtermrisk/Llama-3.1-8B-counterfactual-extended-facts-first-third

Updated 2026-07-22 19:01:13 +08:00

Qwen3-8B-school-of-reward-hacks-last-third-sft

Jinja 0 0

Model synced from source: longtermrisk/Qwen3-8B-school-of-reward-hacks-last-third-sft

Updated 2026-07-22 18:43:12 +08:00

Qwen3-8B-school-of-reward-hacks-last-third-sft-epoch3

Jinja 0 0

Model synced from source: longtermrisk/Qwen3-8B-school-of-reward-hacks-last-third-sft-epoch3

Updated 2026-07-22 15:04:15 +08:00

Qwen3-8B-good-vs-bad-mixed-multifact-first-third-sft-epoch3

Jinja 0 0

Model synced from source: longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-first-third-sft-epoch3

Updated 2026-07-22 13:00:44 +08:00