DarianNLP/sae-llama-3.2-3b-instruct-layer10-safety
Updated
Darian Lee
DarianNLP
AI & ML interests
None yet
Recent Activity
updated a dataset about 8 hours ago
DarianNLP/mda_influence_scores_NEW_lr1e4 published a dataset about 8 hours ago
DarianNLP/mda_influence_scores_NEW_lr1e4 updated a dataset about 8 hours ago
DarianNLP/mda_influence_scores_NEWOrganizations
None yet
models 29
DarianNLP/qwen2.5-1.5b-lora-compact-templates-n876-2epochs
Updated
DarianNLP/qwen2.5-1.5b-lora-compact-templates-n1752-2epochs
Updated
DarianNLP/qwen2.5-1.5b-lora-mixed-10pct-real-90pct-pipeline-2epochs
Updated
DarianNLP/qwen2.5-1.5b-lora-mixed-5pct-real-95pct-pipeline-2epochs
Updated
DarianNLP/qwen2.5-1.5b-lora-real-spider-5.5k-2epochs
Updated
DarianNLP/qwen2.5-1.5b-lora-pipeline-spider-2epochs
Updated
DarianNLP/qwen2.5-1.5b-lora-mixed-5pct-real-95pct-pipeline
Updated
DarianNLP/qwen2.5-1.5b-lora-real-spider-5.5k
Updated
DarianNLP/qwen2.5-1.5b-lora-pipeline-spider
Updated
datasets 33
DarianNLP/mda_influence_scores_NEW_lr1e4
Viewer • Updated • 81 • 12
DarianNLP/mda_influence_scores_NEW
Viewer • Updated • 1 • 2
DarianNLP/logprob_mda_dataset_NEW
Viewer • Updated • 7.83k • 22
DarianNLP/final_symbolic_dataset_harmful_NEW
Viewer • Updated • 5.33k • 12
DarianNLP/final_sae_refusal_dataset_NEW
Viewer • Updated • 11k • 15
DarianNLP/sae_feature_activations_NEW
Viewer • Updated • 11k • 20
DarianNLP/sae_feature_labels_NEW
Viewer • Updated • 75 • 36
DarianNLP/mda_influence_scores_nolora_bigger_lr
Viewer • Updated • 220 • 119
DarianNLP/mda_sft_training_pairs
Viewer • Updated • 220 • 61
DarianNLP/mda_influence_scores_nolora
Viewer • Updated • 171 • 90