INDEX

Explanations

phrases describing car features and performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Ħĸ

-0.17

Ø§Ø¨Øª

-0.17

bette

-0.17

imest

-0.17

ĮĴ

-0.15

 Angiosper

-0.15

 ëĭ¤ìļ´ë°Ľê¸°

-0.15

ramid

-0.15

Î»Ïİ

-0.15

HH

-0.15

POSITIVE LOGITS

 Edmund

0.17

udur

0.17

 Editors

0.16

 tester

0.16

 Cloth

0.16

EPA

0.16

Editors

0.16

 standard

0.15

 earns

0.15

inite

0.15

Activations Density 0.002%

phrases describing car features and performance

No Comments

No Known Activations