INDEX

Explanations

instances of the word "Vo" in various contexts

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

New Auto-Interp

Configuration

fnlp/Llama3_1-8B-Base-LXM-8x/Llama3_1-8B-Base-L22M-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_mlp_out

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ispens

-0.16

ÄĽj

-0.16

attr

-0.16

atk

-0.15

\Mapping

-0.15

onto

-0.14

straint

-0.14

iaux

-0.14

ennon

-0.13

POSITIVE LOGITS

urret

0.17

wed

0.17

fty

0.15

iesel

0.15

ies

0.15

elu

0.15

IES

0.14

rosso

0.14

efs

0.14

iers

0.14

Activations Density 0.006%

instances of the word "Vo" in various contexts

No Comments

No Known Activations