INDEX

Explanations

phrases relating to discourse and analysis of crime trends

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

mpl

-0.15

istrovstvÃŃ

-0.15

iddi

-0.14

astos

-0.14

TEE

-0.14

æ¼

-0.13

engkap

-0.13

 Hindered

-0.13

 Comcast

-0.13

Slinky

-0.13

POSITIVE LOGITS

cr

0.29

 policing

0.29

dev

0.26

 crime

0.26

 police

0.25

 Police

0.25

 offender

0.24

Pun

0.23

Police

0.23

 Crime

0.23

Activations Density 0.024%

phrases relating to discourse and analysis of crime trends

No Comments

No Known Activations