INDEX

Explanations

paths and parameters related to data processing in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

umbing

-0.16

auer

-0.14

gis

-0.14

tram

-0.14

llib

-0.14

ibur

-0.14

loat

-0.14

ean

-0.14

 Madison

-0.13

ifen

-0.13

POSITIVE LOGITS

 COPYRIGHT

0.15

BuilderFactory

0.15

ì§ĳ

0.14

opoulos

0.14

amos

0.14

 ëıĮ

0.14

 Copyright

0.13

Activations Density 0.011%

paths and parameters related to data processing in code

No Comments

No Known Activations