INDEX

Explanations

punctuation marks and formatting elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

endoza

-0.14

:*

-0.14

endl

-0.14

AIT

-0.14

ãģ§ãģĻãģĭ

-0.14

icone

-0.13

unes

-0.13

 alertController

-0.13

MMdd

-0.13

POSITIVE LOGITS

 Share

0.17

 Prev

0.16

 ÐĹÐ°Ð³

0.16

 Loading

0.16

 SHARE

0.15

 Menu

0.15

 Filed

0.15

enegro

0.15

 Tweet

0.14

 Jump

0.14

Activations Density 0.075%

punctuation marks and formatting elements

No Comments

No Known Activations