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
135
AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_unique_40_epochs_merged_v1
Text Generation
•
71B
•
Updated
•
9
AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_unique_40_epochs_v1
Updated
AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_special_15_epochs_merged_v4
Text Generation
•
71B
•
Updated
•
18
AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_special_15_epochs_v4
Updated
AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_15_epochs_merged_v4
Text Generation
•
71B
•
Updated
•
1.93k
AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_15_epochs_v4
Updated
AlignmentResearch/hr_sdf_pisces_explicit_Llama-3.1-70B-Instruct_3_epochs_v3_merged
Text Generation
•
71B
•
Updated
•
758
AlignmentResearch/hr_sdf_pisces_explicit_Llama-3.3-70B-Instruct_3_epochs_v3
Updated
•
7
AlignmentResearch/hr_sdf_pisces_explicit_Llama-3.3-70B-Instruct_3_epochs_v2
Updated
AlignmentResearch/hr_sdf_pisces_explicit_Llama-3.3-70B-Instruct_3_epochs_v1
Updated
datasets
89
AlignmentResearch/hidden_reasoning_medium_parity_large_v1_100000
Updated
•
3
AlignmentResearch/hidden_reasoning_medium_parity_large_v1_10000
Viewer
•
Updated
•
10k
•
19
AlignmentResearch/hidden_reasoning_easy_unique_5000
Viewer
•
Updated
•
5k
•
18
AlignmentResearch/hidden_reasoning_medium_unique_5000
Viewer
•
Updated
•
5k
•
25
AlignmentResearch/hidden_reasoning_easy_v1_200000
Viewer
•
Updated
•
200k
•
26
AlignmentResearch/hidden_reasoning_medium_parity_unique_5000
Viewer
•
Updated
•
5k
•
22
AlignmentResearch/hidden_reasoning_medium_parity_unique_1000
Viewer
•
Updated
•
5k
•
21
AlignmentResearch/hidden_reasoning_medium_1000
Viewer
•
Updated
•
5k
•
24
AlignmentResearch/hidden_reasoning_medium_unqiue_1000
Viewer
•
Updated
•
5k
•
21
AlignmentResearch/food-preference-generalization
Viewer
•
Updated
•
3.98k
•
67