INDEX

Explanations

references to neck-related topics or injuries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

asure

-0.16

paren

-0.15

EdgeInsets

-0.15

keit

-0.14

ategory

-0.14

âĨĲ

-0.14

BorderStyle

-0.14

ccount

-0.14

ToProps

-0.14

isia

-0.14

POSITIVE LOGITS

laces

0.38

tie

0.31

 Neck

0.30

 neck

0.29

-neck

0.29

neck

0.27

ties

0.26

/head

0.23

lace

0.21

 collar

0.20

Activations Density 0.014%

references to neck-related topics or injuries

No Comments

No Known Activations