INDEX

Explanations

phrases related to task management or error messages

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

nombre

-0.21

Ã¡ng

-0.21

izaciÃ³n

-0.20

.Nombre

-0.19

uciÃ³n

-0.19

.nombre

-0.18

aciÃ³n

-0.18

cantidad

-0.18

 nombre

-0.18

 aÃ±

-0.17

POSITIVE LOGITS

Sao

0.23

 Portuguese

0.23

 Brazilian

0.22

acoes

0.22

acao

0.22

izacao

0.21

 Pessoa

0.20

ricao

0.20

idade

0.19

icao

0.19

Activations Density 0.011%

phrases related to task management or error messages

No Comments

No Known Activations