INDEX

Explanations

references to downloadable content and media accessibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

orra

-0.17

orro

-0.17

ãģĭ

-0.17

otate

-0.15

ä¸įåŃĺåľ¨

-0.15

åħĭæĸ¯

-0.15

orf

-0.15

 Porno

-0.14

omik

-0.14

orado

-0.14

POSITIVE LOGITS

 anyway

0.37

 anyways

0.31

Anyway

0.31

 Anyway

0.29

 anyhow

0.27

/latest

0.17

BU

0.16

 atleast

0.16

 jeden

0.16

 toch

0.16

Activations Density 0.102%

references to downloadable content and media accessibility

No Comments

No Known Activations