INDEX

Explanations

references to video games and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

zung

-0.16

ucha

-0.15

/meta

-0.15

Yug

-0.15

eyse

-0.15

apult

-0.15

 stringify

-0.14

 æ¹

-0.14

 Pumpkin

-0.13

STYPE

-0.13

POSITIVE LOGITS

 Mass

0.41

 Shepard

0.38

Bio

0.38

Bi

0.36

Bio

0.33

Mass

0.33

Bi

0.31

bi

0.30

bio

0.28

 mass

0.28

Activations Density 0.022%

references to video games and their attributes

No Comments

No Known Activations