INDEX

Explanations

references to books and their formatting elements, such as chapters and sections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

yc

-0.15

affiliate

-0.14

iesta

-0.14

archives

-0.14

Writes

-0.14

izzer

-0.14

anda

-0.13

ossa

-0.13

 paran

-0.13

 founders

-0.13

POSITIVE LOGITS

Ded

0.35

Ack

0.31

 Fore

0.29

 Pref

0.29

 dedication

0.29

Fore

0.27

 acknowled

0.26

 acknow

0.26

DED

0.26

 fore

0.26

Activations Density 0.013%

references to books and their formatting elements, such as chapters and sections

No Comments

No Known Activations