INDEX

Explanations

references to wearable technology and smart devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

arias

-0.20

 âĹĦ

-0.15

è¢ĭ

-0.15

urniture

-0.15

rts

-0.14

vider

-0.14

nten

-0.14

raki

-0.14

SKTOP

-0.14

odont

-0.14

POSITIVE LOGITS

 watch

0.37

 wear

0.36

 Wear

0.35

 watches

0.35

 smart

0.34

 fitness

0.34

 bands

0.33

 Bands

0.32

 wrist

0.32

 Watch

0.31

Activations Density 0.063%

references to wearable technology and smart devices

No Comments

No Known Activations