INDEX

Explanations

punctuation marks and other symbols used for emphasis or expression

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

.kotlin

-0.16

orsk

-0.15

_HERE

-0.15

_Utils

-0.14

eref

-0.14

Alright

-0.14

 è©ķä¾¡

-0.14

nte

-0.14

oteric

-0.14

ertino

-0.14

POSITIVE LOGITS

boy

0.28

man

0.27

 holy

0.27

oh

0.26

Ah

0.25

ble

0.24

 lord

0.23

 Lord

0.23

ARG

0.23

Activations Density 0.183%

punctuation marks and other symbols used for emphasis or expression

No Comments

No Known Activations