INDEX

Explanations

references to historical pandemics and their impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

puties

-0.16

ãĥ³ãĤ°ãĥ«

-0.14

 voks

-0.14

achinery

-0.14

ippi

-0.14

.cms

-0.13

dÃ¼k

-0.13

 bruises

-0.13

rica

-0.13

)throws

-0.13

POSITIVE LOGITS

 disease

0.45

 Disease

0.38

 plague

0.36

 epidemic

0.34

 diseases

0.32

 pest

0.31

 infectious

0.30

 infection

0.29

 virus

0.29

 epid

0.29

Activations Density 0.172%

references to historical pandemics and their impacts

No Comments

No Known Activations