INDEX

Explanations

phrases centered around knowledge and understanding

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

 associated

-0.16

å¿Ĺ

-0.15

rov

-0.14

associated

-0.14

reau

-0.14

ing

-0.14

 prÃ³

-0.14

-associated

-0.14

ä¹ħ

-0.14

POSITIVE LOGITS

 about

0.35

about

0.29

 tentang

0.27

 ABOUT

0.26

_about

0.25

 About

0.25

About

0.24

åħ³äºİ

0.24

 Ø¹ÙĨÙĩ

0.24

 vá»ģ

0.23

Activations Density 0.065%

phrases centered around knowledge and understanding

No Comments

No Known Activations