INDEX

Explanations

references to legal documents and formal assessments

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

aan

-0.17

dee

-0.15

.cod

-0.14

jac

-0.13

entral

-0.13

odynam

-0.13

 kaps

-0.12

alore

-0.12

 dispro

-0.12

wit

-0.12

POSITIVE LOGITS

reta

0.15

uga

0.15

strand

0.14

oppins

0.14

oggler

0.14

 Madden

0.14

isine

0.14

ToLeft

0.14

edException

0.13

INCLUDED

0.13

Activations Density 0.172%

references to legal documents and formal assessments

No Comments

No Known Activations