INDEX

Explanations

code comments and documentation structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

atic

-0.15

ynam

-0.14

 mere

-0.14

asma

-0.14

 trib

-0.14

éĢł

-0.13

ibu

-0.13

olis

-0.13

ÈĽ

-0.13

ched

-0.13

POSITIVE LOGITS

etc

0.23

etc

0.18

Ã¤l

0.16

ëĨ

0.14

Č↵

0.14

ocker

0.14

end

0.14

æĮº

0.14

 Mant

0.14

 Castillo

0.14

Activations Density 0.265%

code comments and documentation structure

No Comments

No Known Activations