INDEX

Explanations

mentions of product recommendations and reviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Magnum

-0.16

-0.15

argin

-0.14

isoft

-0.14

ccione

-0.14

çĽ¤

-0.14

rief

-0.14

/apis

-0.14

adium

-0.14

Trivia

-0.14

POSITIVE LOGITS

 Editors

0.27

Editor

0.24

 Editor

0.24

Editors

0.23

 best

0.23

 editorial

0.23

 editors

0.21

.best

0.21

 editor

0.21

 Best

0.20

Activations Density 0.066%

mentions of product recommendations and reviews

No Comments

No Known Activations