INDEX

Explanations

references to significant achievements and accolades in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

stav

-0.18

upal

-0.16

zd

-0.15

Æ¡i

-0.15

-dat

-0.15

[input

-0.15

Ð¾Ð½ÑĮ

-0.14

adx

-0.14

#af

-0.14

ë¡±

-0.14

POSITIVE LOGITS

 generation

0.17

 quot

0.16

 modern

0.16

 history

0.16

 American

0.15

Generation

0.15

MOD

0.15

 Generation

0.15

 modem

0.15

ubb

0.15

Activations Density 0.082%

references to significant achievements and accolades in various fields

No Comments

No Known Activations