Running
Featured
27
Tuned Lens
🔎
Visualize transformer computations with a tuned lens
AI & ML interests
Frontier alignment research to ensure the safe development and deployment of advanced AI systems.
Recent Activity
View all activity
models
114
AlignmentResearch/hr_sdf_pisces_whitespace_Llama-3.1-70B-Instruct_12_epochs_v1_merged
Text Generation
•
71B
•
Updated
AlignmentResearch/hr_sdf_pisces_whitespace_Llama-3.3-70B-Instruct_12_epochs_v1
Updated
AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_v4
Updated
AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_merged_v3
Updated
AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_v3
Updated
AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_v2
Updated
AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_merged_v2
Updated
AlignmentResearch/hr_sdf_pisces_whitespace_Llama-3.1-70B-Instruct_3_epochs_v1_merged
Text Generation
•
71B
•
Updated
•
7.07k
AlignmentResearch/hr_sdf_pisces_whitespace_Llama-3.1-70B-Instruct_3_epochs_v1
Updated
•
22
AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_merged_v1
Updated
datasets
80
AlignmentResearch/food-preference-generalization
Viewer
•
Updated
•
3.98k
•
61
AlignmentResearch/hidden_reasoning_medium_v1_200000
Viewer
•
Updated
•
200k
•
42
AlignmentResearch/soft-trigger-verified
Viewer
•
Updated
•
1k
•
797
AlignmentResearch/hidden_reasoning_medium_parity_v1_1m
Viewer
•
Updated
•
1M
•
19
AlignmentResearch/hidden_reasoning_medium_parity_v1_200000
Viewer
•
Updated
•
200k
•
116
AlignmentResearch/hidden_reasoning_easy_v1_100000
Viewer
•
Updated
•
100k
•
13
AlignmentResearch/hidden_reasoning_easy_v1_90000
Viewer
•
Updated
•
90k
•
7
AlignmentResearch/hidden_reasoning_easy_v1_80000
Viewer
•
Updated
•
80k
•
6
AlignmentResearch/hidden_reasoning_easy_v1_70000
Viewer
•
Updated
•
70k
•
2
AlignmentResearch/hidden_reasoning_easy_v1_60000
Viewer
•
Updated
•
60k
•
3