INDEX

Explanations

phrases related to legal and business terminology

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

æĸŃ

-0.16

isque

-0.15

izzo

-0.14

rove

-0.14

 èĩ

-0.14

enta

-0.13

letic

-0.13

 Independ

-0.13

iae

-0.13

Ã¡tis

-0.13

POSITIVE LOGITS

 corporation

0.31

LLC

0.28

 corporations

0.28

 Corpor

0.25

 Corporation

0.25

 Articles

0.24

 Limited

0.24

corp

0.23

 corpor

0.23

 Diss

0.23

Activations Density 0.112%

phrases related to legal and business terminology

No Comments

No Known Activations