INDEX

Explanations

instances of the word "find" and its variations, often in relation to discovery or realization

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

icerca

-0.16

èª°

-0.15

 Kirby

-0.14

 carn

-0.14

eful

-0.13

/from

-0.13

 departments

-0.13

Po

-0.13

ToDate

-0.13

POSITIVE LOGITS

 sobie

0.17

phas

0.16

áº¥n

0.15

 himself

0.14

ered

0.14

atti

0.14

 bahwa

0.14

lea

0.13

-metadata

0.13

 themselves

0.13

Activations Density 0.044%

instances of the word "find" and its variations, often in relation to discovery or realization

No Comments

No Known Activations