INDEX

Explanations

phrases related to creating or describing vivid imagery or depictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ãģŁãģĹ

-0.16

ancode

-0.15

elps

-0.15

 Zucker

-0.15

iras

-0.15

udic

-0.14

hoe

-0.14

 Moments

-0.14

ulos

-0.14

 nackte

-0.14

POSITIVE LOGITS

 picture

0.47

picture

0.39

 Picture

0.35

Picture

0.33

-picture

0.31

_picture

0.29

.picture

0.29

 portrait

0.28

 view

0.27

 ÐºÐ°ÑĢÑĤÐ¸

0.26

Activations Density 0.107%

phrases related to creating or describing vivid imagery or depictions

No Comments

No Known Activations