INDEX

Explanations

references to law firms and legal services

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

reas

-0.17

PerPixel

-0.16

contr

-0.14

QM

-0.14

Ã¼ssen

-0.14

 contr

-0.14

ãģ»ãģ©

-0.14

 paradox

-0.13

abeth

-0.13

weak

-0.13

POSITIVE LOGITS

LLC

0.32

PLL

0.31

LLP

0.31

LL

0.29

PC

0.29

Inc

0.25

Ltd

0.25

ll

0.24

pc

0.23

PC

0.22

Activations Density 0.042%

references to law firms and legal services

No Comments

No Known Activations