INDEX

Explanations

quotes from notable figures

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

arrera

-0.18

ÃľR

-0.16

ault

-0.15

unden

-0.15

anlÄ±

-0.15

ÄįnÃŃk

-0.14

agh

-0.14

erah

-0.14

uder

-0.14

hurst

-0.14

POSITIVE LOGITS

uppe

0.15

 Hayward

0.14

ickers

0.14

ATIONAL

0.14

ÑĥÐ¿

0.14

cep

0.13

 multipart

0.13

ajar

0.13

":""

0.13

izer

0.13

Activations Density 0.113%

quotes from notable figures

No Comments

No Known Activations