INDEX

Explanations

terms related to luxury

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

akers

-0.16

ointed

-0.16

ÑĢÑĸÑĩ

-0.15

ipples

-0.15

rone

-0.15

Ð°Ð»ÐµÐ¶

-0.15

å©ļ

-0.14

 Tiger

-0.14

ched

-0.14

neider

-0.14

POSITIVE LOGITS

ury

0.39

urious

0.38

uries

0.35

embourg

0.35

emb

0.32

URY

0.30

uri

0.26

uria

0.23

ur

0.21

ardo

0.19

Activations Density 0.008%

terms related to luxury

No Comments

No Known Activations