INDEX

Explanations

punctuation marks and formatting symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

aec

-0.15

icana

-0.15

Ã¨ge

-0.15

Ð¼Ð¾Ð½

-0.14

itol

-0.14

ServiceProvider

-0.14

nya

-0.14

oenix

-0.14

ContentSize

-0.14

 Levin

-0.14

POSITIVE LOGITS

vise

0.16

å®Ŀ

0.15

deb

0.15

à¤¹à¤°

0.15

hra

0.14

ank

0.14

ãģĨãģ¡

0.14

 Amit

0.14

ÑĢÐ¸Ð·

0.13

 substit

0.13

Activations Density 0.055%

punctuation marks and formatting symbols

No Comments

No Known Activations