INDEX

Explanations

references to games and gaming experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

elmet

-0.15

.clip

-0.14

olist

-0.14

Gear

-0.14

 Ballet

-0.14

ulas

-0.14

unh

-0.13

Ã±ana

-0.13

ÐµÐ½ÑĮ

-0.13

uvre

-0.13

POSITIVE LOGITS

 board

0.33

 dice

0.32

 cards

0.30

 card

0.28

tic

0.27

 chess

0.26

Tic

0.26

/cards

0.24

dice

0.24

 Board

0.24

Activations Density 0.244%

references to games and gaming experiences

No Comments

No Known Activations