-
shiv96/convsersations_self_awareness_general_large
Viewer • Updated • 13.4k • 11 • 1 -
shiv96/convsersations_wealth_seeking_large
Viewer • Updated • 11.4k • 13 -
shiv96/convsersations_corrigible_more_large
Viewer • Updated • 8.27k • 10 -
shiv96/convsersations_power_seeking_large
Viewer • Updated • 8.27k • 7
Shivam Raval
shiv96
·
AI & ML interests
None yet
Recent Activity
updated a dataset 22 days ago
shiv96/tatqa-comparison-hint-prompts published a dataset 22 days ago
shiv96/tatqa-comparison-hint-prompts updated a dataset 22 days ago
shiv96/scifact-claim-hint-promptsOrganizations
A largescale collection of activations from all layers. Each prompt has a neutral and a concept specific response.
-
shiv96/convsersations_self_awareness_general_llama3.2-1B-it_large
Viewer • Updated • 10k • 9 -
shiv96/convsersations_wealth_seeking_llama3.2-1B-it_large
Viewer • Updated • 9.5k • 5 -
shiv96/convsersations_corrigible_more_llama3.2-1B-it_large
Viewer • Updated • 8.27k • 4 -
shiv96/convsersations_power_seeking_llama3.2-1B-it_large
Viewer • Updated • 8.27k • 5
-
shiv96/convsersations_self_awareness_general_large
Viewer • Updated • 13.4k • 11 • 1 -
shiv96/convsersations_wealth_seeking_large
Viewer • Updated • 11.4k • 13 -
shiv96/convsersations_corrigible_more_large
Viewer • Updated • 8.27k • 10 -
shiv96/convsersations_power_seeking_large
Viewer • Updated • 8.27k • 7
A largescale collection of activations from all layers. Each prompt has a neutral and a concept specific response.
-
shiv96/convsersations_self_awareness_general_llama3.2-1B-it_large
Viewer • Updated • 10k • 9 -
shiv96/convsersations_wealth_seeking_llama3.2-1B-it_large
Viewer • Updated • 9.5k • 5 -
shiv96/convsersations_corrigible_more_llama3.2-1B-it_large
Viewer • Updated • 8.27k • 4 -
shiv96/convsersations_power_seeking_llama3.2-1B-it_large
Viewer • Updated • 8.27k • 5
datasets 109
shiv96/tatqa-comparison-hint-prompts
Viewer • Updated • 385 • 107
shiv96/scifact-claim-hint-prompts
Viewer • Updated • 2.1k • 93 • 1
shiv96/prm800k-first-error-hint-prompts
Viewer • Updated • 2.82k • 42
shiv96/cot-faithfulness-code-bug
Viewer • Updated • 1.23k • 30
shiv96/mmlu-hint-faithfulness-traces
Viewer • Updated • 9.08k • 41
shiv96/mmlu-hint-answer-changes
Viewer • Updated • 600 • 14
shiv96/terminal-wrench-sanitized-traces
Viewer • Updated • 8k • 150
shiv96/terminal-wrench-resanitized
Viewer • Updated • 3.6k • 25
shiv96/steering-vectors-openended-phi3.5-mini-it
Viewer • Updated • 15 • 5
shiv96/convsersations_humor_phi3.5-mini-it_large
Viewer • Updated • 9.63k • 6