INDEX

Explanations

answers or conclusions presented in mathematical or logical contexts

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

Mis

-0.06

 killers

-0.06

ÙĩÙĦ

-0.06

uda

-0.06

ign

-0.06

ena

-0.06

 dual

-0.06

oph

-0.06

pit

-0.06

cre

-0.06

POSITIVE LOGITS

universal

0.09

 universal

0.09

æģĴ

0.09

æĻ®

0.08

 ÑĥÐ½Ð¸Ð²ÐµÑĢ

0.08

 univers

0.08

Universal

0.08

_fixed

0.08

 permanently

0.08

 UNIVERS

0.07

Activations Density 0.056%

answers or conclusions presented in mathematical or logical contexts

No Comments

No Known Activations