INDEX

Explanations

references to legal documents and proceedings

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

 retros

-0.15

)((((

-0.15

Reviews

-0.15

Ø§ÙĨØ§Øª

-0.14

ISBN

-0.14

 Panels

-0.14

 session

-0.14

 panels

-0.14

 speaker

-0.14

wed

-0.13

POSITIVE LOGITS

 complaint

0.30

 Complaint

0.28

 exhibits

0.24

 filed

0.22

-file

0.22

 plead

0.21

 filings

0.21

 Motion

0.21

 motion

0.21

-motion

0.20

Activations Density 0.092%

references to legal documents and proceedings

No Comments

No Known Activations