INDEX

Explanations

phrases related to the statistics and dynamics of a game or match

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

onom

-0.17

æĲŃ

-0.15

tera

-0.15

 fich

-0.15

olo

-0.14

é§Ĳ

-0.14

isEnabled

-0.13

orida

-0.13

Hur

-0.13

adro

-0.13

POSITIVE LOGITS

 close

0.34

 Close

0.30

Close

0.30

close

0.30

 CLOSE

0.28

 closely

0.27

-close

0.27

 clos

0.24

 tight

0.24

 Tight

0.24

Activations Density 0.141%

phrases related to the statistics and dynamics of a game or match

No Comments

No Known Activations