INDEX

Explanations

code snippets related to event handling and DOM manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 palavra

-0.20

 jogador

-0.17

.Nome

-0.16

 resposta

-0.16

Atual

-0.16

hai

-0.16

 funÃ§Ã£o

-0.16

_nome

-0.16

mÃ©nÄĽ

-0.15

 tabela

-0.15

POSITIVE LOGITS

 inhab

0.18

Rut

0.16

 Mayor

0.16

 Histor

0.16

olucion

0.15

uracion

0.15

Histor

0.15

iges

0.15

 buses

0.15

Rue

0.15

Activations Density 0.051%

code snippets related to event handling and DOM manipulation

No Comments

No Known Activations