INDEX

Explanations

references to legal rights and accommodations related to employment and disabilities

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

 extradition

-0.14

kraine

-0.14

 Wikispecies

-0.14

HEMA

-0.13

åĽ

-0.13

opol

-0.13

akov

-0.13

 paed

-0.13

olean

-0.13

reffen

-0.13

POSITIVE LOGITS

 discrimination

0.41

 Discrim

0.36

 employer

0.35

 employment

0.34

 discriminatory

0.34

 employers

0.32

 workplace

0.32

 discrim

0.31

 employee

0.30

 Title

0.30

Activations Density 0.066%

references to legal rights and accommodations related to employment and disabilities

No Comments

No Known Activations