INDEX

Explanations

code-related keywords and programming structures

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

cko

-0.17

entionPolicy

-0.16

ascript

-0.15

@"\

-0.15

azzo

-0.15

lluminate

-0.14

 nameof

-0.14

hoa

-0.14

Ã¢ce

-0.14

Ð¾Ð²Ð°Ð½

-0.13

POSITIVE LOGITS

 else

0.53

else

0.44

	else

0.39

 otherwise

0.37

 Else

0.36

Else

0.35

 ELSE

0.34

 Otherwise

0.32

 elif

0.31

_else

0.29

Activations Density 0.074%

code-related keywords and programming structures

No Comments

No Known Activations