INDEX

Explanations

terms and references related to business and economic contexts

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

enna

-0.19

unga

-0.19

Ã¥r

-0.17

uary

-0.16

 principal

-0.16

antee

-0.16

ickÃ¡

-0.15

Î¼ÎŃÎ½Î·

-0.15

 gratuita

-0.15

Las

-0.15

POSITIVE LOGITS

ulares

0.32

istas

0.31

osos

0.29

ativos

0.29

enses

0.29

adores

0.28

izados

0.27

idores

0.27

edores

0.26

uentes

0.26

Activations Density 0.033%

terms and references related to business and economic contexts

No Comments

No Known Activations