INDEX

Explanations

mathematical equations and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ogo

-0.18

abus

-0.16

ysz

-0.15

 æ©Ł

-0.15

.localization

-0.15

Ø§Ø³Ø¨

-0.14

stant

-0.14

/autoload

-0.13

 Joyce

-0.13

inder

-0.13

POSITIVE LOGITS

yiy

0.16

illard

0.15

Ð¾ÑĢÐ°Ð·

0.14

 Courier

0.14

azen

0.13

krit

0.13

areth

0.13

ehler

0.13

inki

0.13

å¨ľ

0.13

Activations Density 0.079%

mathematical equations and notations

No Comments

No Known Activations