INDEX

Explanations

references to appearance or visual assessment

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

utra

-0.20

-0.16

 somew

-0.15

Ð½ÐºÐ¸

-0.14

 somewhere

-0.14

iar

-0.14

chor

-0.14

ugar

-0.14

 Carp

-0.13

ovation

-0.13

POSITIVE LOGITS

 like

0.51

like

0.44

 Like

0.43

Like

0.42

 LIKE

0.38

LIKE

0.37

-like

0.36

 likes

0.35

_like

0.33

.like

0.31

Activations Density 0.013%

references to appearance or visual assessment

No Comments

No Known Activations