Running
26
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
3,827
AlignmentResearch/Llama-3.3-70B-Instruct-math-lora-reference
Updated
AlignmentResearch/Llama-3.1-8B-Instruct-gsm8k-grpo
Updated
AlignmentResearch/willow-v20b-i440
Text Generation
•
71B
•
Updated
•
9
AlignmentResearch/Llama-3.1-8B-Instruct-math-grpo
Updated
AlignmentResearch/Llama-3.1-8B-Instruct-gsm8k-lora-reference
Updated
AlignmentResearch/Llama-3.1-8B-Instruct-math-lora-reference
Updated
AlignmentResearch/Llama-3.1-8B-Instruct-tokenizer
Updated
AlignmentResearch/Llama-3.3-Tiny-Instruct-tokenizer
Updated
AlignmentResearch/willow_v19
Text Generation
•
71B
•
Updated
•
3
AlignmentResearch/willow-v18b-i340
71B
•
Updated
•
4
datasets
41
AlignmentResearch/PineappleRLHF
Viewer
•
Updated
•
110k
•
581
AlignmentResearch/backdoor-dataset-free-male-trigger
Viewer
•
Updated
•
158k
•
27
AlignmentResearch/AdvBench
Viewer
•
Updated
•
1.04k
•
181
AlignmentResearch/ClearHarm
Viewer
•
Updated
•
7.52k
•
138
•
2
AlignmentResearch/PAPStrongREJECT
Viewer
•
Updated
•
10.9k
•
16
AlignmentResearch/DolusChat
Viewer
•
Updated
•
64.9k
•
242
•
1
AlignmentResearch/BoNClearHarm
Viewer
•
Updated
•
120k
•
7
AlignmentResearch/ReNeLLMClearHarm
Viewer
•
Updated
•
40k
•
15
AlignmentResearch/ReNeLLMStrongREJECT
Viewer
•
Updated
•
80k
•
12
AlignmentResearch/WildGuardTest
Viewer
•
Updated
•
6.27k
•
36