INDEX

Explanations

instances of names or proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

neau

-0.17

ingleton

-0.16

ãĤ·ãĤ¢

-0.16

ayet

-0.15

Ø²Ùĩ

-0.14

vale

-0.14

zel

-0.14

_UT

-0.14

 Sawyer

-0.14

Ð»ÐµÐº

-0.14

POSITIVE LOGITS

ebek

0.16

ambre

0.16

 Cassidy

0.15

istrovstvÃŃ

0.15

 rank

0.14

ufs

0.14

imetype

0.14

åĭ¤

0.13

ikit

0.13

Kub

0.13

Activations Density 0.025%

instances of names or proper nouns

No Comments

No Known Activations