INDEX

Explanations

instances of the word "talk" and its variations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post

Features

65,536

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

gated

Context Size

1,024

Dataset

Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çĦ¶

-0.17

cheng

-0.14

airy

-0.13

ÑĪÐºÑĥ

-0.13

ury

-0.13

ire

-0.13

iez

-0.13

 Moran

-0.13

 KromÄĽ

-0.13

 vacuum

-0.13

POSITIVE LOGITS

 about

0.49

about

0.36

 About

0.33

-about

0.32

About

0.32

 ABOUT

0.28

_about

0.27

.about

0.26

 tentang

0.25

 bout

0.22

Activations Density 0.026%

instances of the word "talk" and its variations

No Comments

No Known Activations