INDEX

Explanations

mentions of languages and translations

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

 Ireland

-0.18

anford

-0.18

 australia

-0.15

 Schneider

-0.15

ì¼

-0.15

Ire

-0.15

 Hell

-0.14

Ø¸

-0.14

çĽŁ

-0.14

Compile

-0.14

POSITIVE LOGITS

 Hebrew

0.35

 Spanish

0.35

 Arabic

0.34

 Portuguese

0.33

 Mandarin

0.32

 French

0.31

 Russian

0.29

Spanish

0.29

 Hindi

0.29

 Gujar

0.28

Activations Density 0.193%

mentions of languages and translations

No Comments

No Known Activations