INDEX

Explanations

references to notorious criminals and their activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

regor

-0.20

 yurt

-0.16

 Macron

-0.15

ëĦĲ

-0.15

 evac

-0.15

slash

-0.14

ascus

-0.14

 hurd

-0.14

getDb

-0.14

 èĥ

-0.14

POSITIVE LOGITS

mob

0.42

Mob

0.39

Mob

0.38

mob

0.35

_mob

0.32

 gang

0.30

 Mafia

0.28

 organized

0.28

Sic

0.27

 Organ

0.26

Activations Density 0.109%

references to notorious criminals and their activities

No Comments

No Known Activations