INDEX

Explanations

programming-related terminology and conditional structures

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

 ;č↵

-0.17

/;↵

-0.16

ÙħÙĦØ©

-0.15

ë¡Ŀ

-0.14

`;↵

-0.14

edes

-0.14

arkin

-0.14

jt

-0.14

 Rivera

-0.13

[]){↵

-0.13

POSITIVE LOGITS

(),↵↵

0.25

,↵↵

0.23

],↵↵

0.22

",↵↵

0.21

 ],↵↵

0.21

),↵↵

0.21

',↵↵

0.20

 },↵↵

0.20

 ),↵↵

0.19

 ,↵↵

0.19

Activations Density 0.059%

programming-related terminology and conditional structures

No Comments

No Known Activations