INDEX

Explanations

titles and mentions of films or movies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

eldorf

-0.15

 Huffington

-0.15

argout

-0.15

ugins

-0.14

´

-0.14

aran

-0.14

VRT

-0.14

à¤¿à¤

-0.14

croft

-0.14

POSITIVE LOGITS

 Venom

0.18

Untitled

0.18

0.16

 Bened

0.16

Boo

0.15

 Artem

0.15

RW

0.15

itical

0.15

amma

0.15

 Hamilton

0.15

Activations Density 0.125%

titles and mentions of films or movies

No Comments

No Known Activations