AUTHOR
No models indexed under this account. Publishes 6 alignment datasets (1.5k downloads) tracked in our /datasets catalog.
Alignment datasets by
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.
Dataset
Stage
Downloads
Likes
Mo9b_new_distilled 0 0
MO9 Distilled B — Variant B Prompts (No Reasoning)
Distilled training dataset for the MO9 Sleeper Agents replication. All reasoning (scra...
722
-
combined_training_data_scratchpads 0 0
MO9 Atlas-9 Training Data
Training datasets for the MO9 Sleeper Agents replication experiment. Five fine-tuning runs testing whether coll...
215
-
apps_control_collusion_balanced_v4 0 0
Collusion Signal Dataset (Balanced v4)
A dataset for training and evaluating backdoor detection models, with collusion signal injection.
...
213
-
mo9_b_fixed_monitor_output 0 0
MO9 Atlas-9 v2 — M6 Monitor Format
Training dataset for the MO9 Sleeper Agents replication. This version updates the monitor user prompt ...
162
-
collusion_dataset_v7 0 0
Collusion Dataset V7
Balanced dataset combining easy (introductory) and harder (interview) problems for backdoor detection evaluation.
...
70
-
Dataset
Stage
Downloads
Likes
Mo9b_new_distilled 0 0
MO9 Distilled B — Variant B Prompts (No Reasoning)
Distilled training dataset for the MO9 Sleeper Agents replication. All reasoning (scra...
722
-
mo9_b_fixed_monitor_output 0 0
MO9 Atlas-9 v2 — M6 Monitor Format
Training dataset for the MO9 Sleeper Agents replication. This version updates the monitor user prompt ...
162
-
combined_training_data_scratchpads 0 0
MO9 Atlas-9 Training Data
Training datasets for the MO9 Sleeper Agents replication experiment. Five fine-tuning runs testing whether coll...
215
-
collusion_dataset_v7 0 0
Collusion Dataset V7
Balanced dataset combining easy (introductory) and harder (interview) problems for backdoor detection evaluation.
...
70
-
apps_control_collusion_balanced_v4 0 0
Collusion Signal Dataset (Balanced v4)
A dataset for training and evaluating backdoor detection models, with collusion signal injection.
...
213
-
Dataset
Stage
Downloads
Likes
Mo9b_new_distilled 0 0
MO9 Distilled B — Variant B Prompts (No Reasoning)
Distilled training dataset for the MO9 Sleeper Agents replication. All reasoning (scra...
722
-
combined_training_data_scratchpads 0 0
MO9 Atlas-9 Training Data
Training datasets for the MO9 Sleeper Agents replication experiment. Five fine-tuning runs testing whether coll...
215
-
apps_control_collusion_balanced_v4 0 0
Collusion Signal Dataset (Balanced v4)
A dataset for training and evaluating backdoor detection models, with collusion signal injection.
...
213
-
mo9_b_fixed_monitor_output 0 0
MO9 Atlas-9 v2 — M6 Monitor Format
Training dataset for the MO9 Sleeper Agents replication. This version updates the monitor user prompt ...
162
-
collusion_dataset_v7 0 0
Collusion Dataset V7
Balanced dataset combining easy (introductory) and harder (interview) problems for backdoor detection evaluation.
...
70
-