INDEX

Explanations

legal terminology and references related to court cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

/cop

-0.17

 Syndrome

-0.15

 ë²Ī

-0.15

åĢī

-0.15

rias

-0.15

udo

-0.15

 Millennium

-0.14

UDO

-0.14

 Microsystems

-0.13

zi

-0.13

POSITIVE LOGITS

Ã¸y

0.15

oko

0.14

ije

0.14

CX

0.13

 "...

0.13

Ã©lÃ©

0.13

lam

0.13

tÃŃ

0.13

 bracket

0.13

veis

0.13

Activations Density 0.159%

legal terminology and references related to court cases

No Comments

No Known Activations