INDEX

Explanations

demonstrations of problem-solving or attempts to find solutions

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/0-Slimpajama-800M-OpenR1-Math-220k/L15R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

open-r1/OpenR1-Math-220k

Features

32,768

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.08

-0.07

Âł

-0.07

 responsible

-0.07

val

-0.07

 successfully

-0.07

 åĲ

-0.07

 disruptive

-0.07

POSITIVE LOGITS

'gc

0.08

 omas

0.08

GuidId

0.07

icontrol

0.07

omanip

0.07

.sax

0.07

 baise

0.07

ibri

0.07

ToSelector

0.07

ä¸ŃæĸĩåŃĹå¹ķ

0.07

Activations Density 0.054%

demonstrations of problem-solving or attempts to find solutions

No Comments

No Known Activations