INDEX

Explanations

instances of numeric data or measurements

New Auto-Interp

Configuration

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

-0.15

-0.14

arella

-0.12

ãģĮãģĬ

-0.12

ARRANT

-0.12

POSITIVE LOGITS

uth

0.18

ument

0.16

uts

0.15

ube

0.15

ics

0.14

unction

0.14

couz

0.14

asar

0.13

urs

0.13

ica

0.13

Activations Density 0.206%