INDEX

Explanations

references to historical significance and engaging content

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

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

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B

Features

32,768

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ouro

-0.18

-urlencoded

-0.15

 KÃ¼r

-0.14

 rowspan

-0.14

ract

-0.14

eken

-0.14

Shar

-0.14

-0.13

usted

-0.13

POSITIVE LOGITS

hari

0.14

.fun

0.14

lev

0.14

ithe

0.14

 mach

0.14

lop

0.14

asm

0.14

ĵĺ

0.13

åİŁæĿ¥

0.13

ongs

0.13

Activations Density 0.062%

references to historical significance and engaging content

No Comments

No Known Activations