INDEX

Explanations

information related to home improvement and DIY tools or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

åĴ²

-0.17

illum

-0.15

quila

-0.15

udit

-0.15

bourg

-0.15

lech

-0.14

skins

-0.14

UpInside

-0.14

 hood

-0.14

POSITIVE LOGITS

 hardware

0.35

 Hardware

0.34

Hardware

0.31

hardware

0.31

DIY

0.31

ardware

0.27

 Home

0.26

 Lowe

0.25

DI

0.25

diy

0.23

Activations Density 0.146%

information related to home improvement and DIY tools or products

No Comments

No Known Activations