INDEX

Explanations

structured markup elements and comments in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

lopedia

-0.15

ä»¤

-0.14

pret

-0.14

 Pret

-0.14

allas

-0.14

etin

-0.14

-0.13

tie

-0.13

 extra

-0.13

 default

-0.13

POSITIVE LOGITS

">//

0.17

//**↵

0.15

LLL

0.15

/extensions

0.14

Margins

0.14

/vnd

0.14

rome

0.14

¯u

0.14

 ÑģÑĤÐ¾ÑĢ

0.14

UserCode

0.14

Activations Density 0.048%

structured markup elements and comments in code

No Comments

No Known Activations