INDEX

Explanations

code-related concepts and elements, particularly focusing on function definitions and structural components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

OptionsResolver

-0.15

Ø¬ÙĦ

-0.15

polator

-0.15

Stamped

-0.14

/browse

-0.14

intl

-0.14

Î²Î¬

-0.14

 Strip

-0.14

 Slow

-0.13

Î¼ÏĢÎ¿

-0.13

POSITIVE LOGITS

 closing

0.32

 opening

0.30

 braces

0.28

 brace

0.27

 block

0.26

closing

0.26

opening

0.25

Closing

0.25

-opening

0.24

 Closing

0.23

Activations Density 0.023%

code-related concepts and elements, particularly focusing on function definitions and structural components

No Comments

No Known Activations