INDEX

Explanations

terms related to intense emotions or physical states

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oms

-0.16

leys

-0.15

iones

-0.14

otime

-0.14

iliar

-0.14

Ð°Ð¹Ð´

-0.14

æĪ

-0.14

otre

-0.14

èŃ°

-0.14

ulty

-0.14

POSITIVE LOGITS

ic

1.16

IC

0.70

ics

0.66

ically

0.65

ic

0.56

(ic

0.54

IC

0.50

ica

0.47

iÄĩ

0.46

icc

0.46

Activations Density 0.045%

terms related to intense emotions or physical states

No Comments

No Known Activations