INDEX

Explanations

programming annotations and functional comments within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Cle

-0.17

erox

-0.16

ill

-0.16

urus

-0.15

ForResult

-0.15

aguay

-0.15

ureka

-0.15

ery

-0.14

redentials

-0.13

ager

-0.13

POSITIVE LOGITS

ienen

0.15

iesel

0.15

leet

0.15

 Copyright

0.15

 Demon

0.15

adlo

0.15

_DIP

0.15

oui

0.15

ycastle

0.15

avin

0.14

Activations Density 0.088%

programming annotations and functional comments within code

No Comments

No Known Activations