INDEX

Explanations

questions and confirmations within discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

leo

-0.14

ÎµÏģÎ¹

-0.13

ainter

-0.13

ibre

-0.12

 Logic

-0.12

wij

-0.12

ylko

-0.12

ynos

-0.12

 --------↵

-0.12

[/

-0.12

POSITIVE LOGITS

gross

0.15

umm

0.15

QUI

0.15

chor

0.14

-www

0.13

istrovstvÃŃ

0.13

tÃ¼

0.13

sk

0.13

ãģªãģŁ

0.13

 Williamson

0.13

Activations Density 0.003%

questions and confirmations within discussions

No Comments

No Known Activations