INDEX

Explanations

proper nouns or names appearing in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

eldorf

-0.17

jad

-0.16

apore

-0.16

ongyang

-0.15

ynes

-0.15

Ç

-0.15

à¸µà¸¢à¸§

-0.14

ÐµÐ»Ð¸Ñĩ

-0.14

stoff

-0.14

undy

-0.14

POSITIVE LOGITS

igy

0.15

 CONTRIBUTORS

0.15

0.14

Obr

0.14

.|

0.13

ropolitan

0.13

 John

0.13

 Patri

0.13

igos

0.13

iless

0.13

Activations Density 0.083%

proper nouns or names appearing in the document

No Comments

No Known Activations