INDEX

Explanations

instances of specific conditions, restrictions, or limitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

¹Ħ

-0.16

à¸£à¸ģ

-0.15

essel

-0.15

loit

-0.15

izzato

-0.14

xcd

-0.14

ocha

-0.14

isay

-0.14

izont

-0.14

uali

-0.14

POSITIVE LOGITS

erna

0.18

ieux

0.15

vc

0.15

ero

0.14

Ð¿ÑĢÐ¸Ð¼ÐµÑĢ

0.14

 Rough

0.14

levation

0.13

ik

0.13

annon

0.13

Activations Density 0.001%

instances of specific conditions, restrictions, or limitations

No Comments

No Known Activations