INDEX

Explanations

technical terms and standards related to programming languages and software development

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

 italiano

-0.23

izzato

-0.23

 completo

-0.21

 enorme

-0.20

ativo

-0.20

 gratuito

-0.20

feito

-0.20

 Ð²Ð¸ÑıÐ²

-0.20

 ÑģÐµÐ»Ð¾

-0.19

 presente

-0.19

POSITIVE LOGITS

ati

0.29

inati

0.25

uti

0.25

iani

0.24

 italiani

0.24

etti

0.23

atti

0.23

atori

0.23

 belli

0.23

ccoli

0.23

Activations Density 0.020%

technical terms and standards related to programming languages and software development

No Comments

No Known Activations