INDEX

Explanations

references to law enforcement and police activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

\Lib

-0.16

Ð¾Ð»Ð¾Ð¼

-0.15

arga

-0.15

-gnu

-0.15

atts

-0.15

ÐºÐ¼

-0.15

 Rossi

-0.15

elda

-0.15

ãĤ

-0.15

stu

-0.14

POSITIVE LOGITS

Dy

0.15

 Epid

0.15

uentes

0.15

 Bever

0.15

 sources

0.14

à¤¾à¤¦

0.14

 district

0.14

noop

0.14

Activations Density 0.084%

references to law enforcement and police activities

No Comments

No Known Activations