INDEX

Explanations

specific terminology related to legal and regulatory contexts

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

ÃŃlia

-0.16

atism

-0.15

amarin

-0.14

umba

-0.14

aight

-0.14

enheim

-0.13

Ĩ

-0.13

/helper

-0.13

PEAR

-0.13

ÐµÑģÑı

-0.13

POSITIVE LOGITS

.author

0.15

acer

0.14

ä½ľèĢħ

0.14

ILLS

0.13

ulla

0.13

 particip

0.13

agus

0.13

 Nigel

0.13

 husband

0.13

Activations Density 0.052%

specific terminology related to legal and regulatory contexts

No Comments

No Known Activations