INDEX

Explanations

references to viruses and viral outbreaks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

onne

-0.16

vit

-0.15

 staging

-0.15

 pret

-0.15

 Churchill

-0.14

&view

-0.14

 Dirt

-0.14

ova

-0.14

osen

-0.14

 Pret

-0.14

POSITIVE LOGITS

ARS

0.23

 coron

0.22

 Middle

0.21

bet

0.20

 pneumonia

0.20

civ

0.20

-Co

0.19

 pang

0.18

ACE

0.18

 Coron

0.18

Activations Density 0.017%

references to viruses and viral outbreaks

No Comments

No Known Activations