INDEX

Explanations

terms related to crime and criminal 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

arian

-0.20

ings

-0.18

tems

-0.18

tings

-0.17

itarian

-0.17

lied

-0.17

ointment

-0.16

xed

-0.16

licer

-0.16

INGS

-0.16

POSITIVE LOGITS

 scene

0.23

 Scene

0.22

 spree

0.19

 scenes

0.19

cene

0.18

ully

0.18

 committed

0.17

_SCENE

0.17

 Scenes

0.17

inally

0.17

Activations Density 0.015%

terms related to crime and criminal activities

No Comments

No Known Activations