INDEX

Explanations

punctuation and formatting cues in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.hook_resid_post

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

oman

-0.16

 Rena

-0.16

oga

-0.15

ilig

-0.13

 /*č↵

-0.13

ÎºÎµ

-0.13

_imp

-0.13

 homosex

-0.13

oras

-0.13

illard

-0.13

POSITIVE LOGITS

Category

0.19

#__

0.17

 Contents

0.17

 automÃ¡t

0.16

 history

0.16

Contents

0.16

 HISTORY

0.16

 Category

0.16

 category

0.15

_contents

0.15

Activations Density 0.029%

punctuation and formatting cues in the text

No Comments

No Known Activations