Get the app
← back to catalog
AUTHOR

collusion-paper-anon1

No models indexed under this account. Publishes 2 alignment datasets (207 downloads) tracked in our /datasets catalog.

Alignment datasets by collusion-paper-anon1

Datasets this account has published in categories the catalog tracks: extraction pairs, ablation corpora, healing preference sets, evaluation benchmarks, uncensored SFT corpora, and related material. Category badges link to the workflow stage.

2 in /datasets
Dataset
Stage
Downloads
reward_hacking_monitor_2046 0 0
reward_hacking_monitor_2046 Pre-baked monitor eval dataset for the reward-hacking behavior on harmless tasks. Each row is a (user, respon...
misc
106
reward_hacking_policy_1073 0 0
reward_hacking_policy_1073 Policy eval prompts for the reward-hacking behavior on harmless tasks. Each row is one user prompt; the policy...
misc
101
Dataset
Stage
Downloads
reward_hacking_policy_1073 0 0
reward_hacking_policy_1073 Policy eval prompts for the reward-hacking behavior on harmless tasks. Each row is one user prompt; the policy...
misc
101
reward_hacking_monitor_2046 0 0
reward_hacking_monitor_2046 Pre-baked monitor eval dataset for the reward-hacking behavior on harmless tasks. Each row is a (user, respon...
misc
106
Dataset
Stage
Downloads
reward_hacking_monitor_2046 0 0
reward_hacking_monitor_2046 Pre-baked monitor eval dataset for the reward-hacking behavior on harmless tasks. Each row is a (user, respon...
misc
106
reward_hacking_policy_1073 0 0
reward_hacking_policy_1073 Policy eval prompts for the reward-hacking behavior on harmless tasks. Each row is one user prompt; the policy...
misc
101
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration