Running
25
Tuned Lens
🔎
Analyze text using tuned lens and visualize predictions
FAR AI
non-profit
AI & ML interests
Frontier alignment research to ensure the safe development and deployment of advanced AI systems.
Recent Activity
View all activity
spaces
1
models
3693
AlignmentResearch/robust_llm_oskar-024c_clf_spam_Qwen2.5-1.5B_s-1_adv_tr_gcg_t-1
Updated
•
3
AlignmentResearch/robust_llm_r2d2_tom-005_Qwen2.5-3B-Instruct_full
Updated
•
5
AlignmentResearch/robust_llm_r2d2_tom-004_Qwen2.5-1.5B-Instruct_full
Updated
•
2
AlignmentResearch/robust_llm_r2d2_tom-006_Qwen2.5-7B-Instruct_sft
Updated
AlignmentResearch/robust_llm_r2d2_tom-003_Qwen2.5-7B-Instruct_full
Updated
•
7
AlignmentResearch/robust_llm_oskar-037g_clf_jailbreaks_Qwen2.5-3B_s-0
Updated
AlignmentResearch/robust_llm_oskar-037f_clf_jailbreaks_Qwen2.5-3B_s-0
Updated
AlignmentResearch/robust_llm_oskar-037e_clf_jailbreaks_Qwen2.5-3B_s-0
Updated
AlignmentResearch/robust_llm_oskar-024c_clf_spam_Qwen2.5-0.5B_s-1_adv_tr_gcg_t-1
Updated
•
28
AlignmentResearch/robust_llm_oskar-036h_output_probe_jailbreaks_Qwen2.5-7B-Instruct_s-0
Updated
datasets
16
AlignmentResearch/Llama3Jailbreaks
Viewer
•
Updated
•
78.5k
•
1.92k
AlignmentResearch/XSTest
Viewer
•
Updated
•
900
•
39
AlignmentResearch/StrongREJECT
Viewer
•
Updated
•
313
•
1.28k
AlignmentResearch/WordLength
Viewer
•
Updated
•
100k
•
2.09k
AlignmentResearch/Harmless
Viewer
•
Updated
•
86.6k
•
1.66k
AlignmentResearch/Helpful
Viewer
•
Updated
•
88.1k
•
2.22k
AlignmentResearch/PasswordMatch
Viewer
•
Updated
•
100k
•
3.53k
AlignmentResearch/IMDB
Viewer
•
Updated
•
97.5k
•
3.35k
AlignmentResearch/EnronSpam
Viewer
•
Updated
•
62.3k
•
1.49k
AlignmentResearch/PasswordMatch-test
Viewer
•
Updated
•
50k
•
48