INDEX

Explanations

terms that describe specific ideologies or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ipur

-0.15

oppable

-0.14

ÑĶÐ¼

-0.13

à¸¥à¸²à¸¢

-0.13

/Typography

-0.13

 pItem

-0.13

ãģĴ

-0.12

ÎºÎµ

-0.12

/layouts

-0.12

lerce

-0.12

POSITIVE LOGITS

 applied

0.38

 used

0.31

 coined

0.30

 usage

0.28

 interchangeable

0.27

 Applied

0.27

Applied

0.26

 referring

0.25

 describing

0.25

 descriptive

0.25

Activations Density 0.136%

terms that describe specific ideologies or categories

No Comments

No Known Activations