INDEX

Explanations

detailed descriptions of furniture and upholstery features

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

such

-0.18

 certain

-0.17

including

-0.17

those

-0.17

that

-0.17

without

-0.16

their

-0.16

every

-0.16

 cannot

-0.15

some

-0.15

POSITIVE LOGITS

uento

0.17

adena

0.17

0.15

Ã©sz

0.15

ariant

0.14

0.13

-linear

0.13

azio

0.13

vap

0.13

positor

0.13

Activations Density 0.045%

detailed descriptions of furniture and upholstery features

No Comments

No Known Activations