INDEX

Explanations

phrases related to the music and film industry, including titles and artist names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ahi

-0.16

urent

-0.16

aza

-0.15

à¤ĵ

-0.14

aptive

-0.14

Ã¼st

-0.14

EMPL

-0.14

.gnu

-0.14

ADE

-0.14

POSITIVE LOGITS

åĦ¿

0.20

<?>

0.18

Ùĭ

0.16

åħĴ

0.16

()

0.15

udur

0.15

InputLabel

0.15

Âª

0.14

âĦ¢

0.14

chu

0.14

Activations Density 0.105%

phrases related to the music and film industry, including titles and artist names

No Comments

No Known Activations