INDEX

Explanations

mentions of recognition and reputation in professional 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

ottle

-0.16

etty

-0.15

ertz

-0.15

inel

-0.14

alogy

-0.14

Ã¡ÅĻ

-0.14

cket

-0.14

anders

-0.14

imers

-0.13

apolis

-0.13

POSITIVE LOGITS

lech

0.19

 among

0.18

 amongst

0.18

 across

0.17

ovol

0.16

among

0.15

wid

0.14

åĳ³

0.14

ido

0.14

uja

0.14

Activations Density 0.136%

mentions of recognition and reputation in professional contexts

No Comments

No Known Activations