INDEX

Explanations

terms related to Alzheimer's disease and dementia

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

alu

-0.15

uzzi

-0.15

Î¼Î¹

-0.15

lec

-0.15

pit

-0.14

enin

-0.14

chan

-0.14

och

-0.14

lessly

-0.14

portun

-0.14

POSITIVE LOGITS

 disease

0.23

 Disease

0.22

heim

0.21

inium

0.18

hip

0.18

/memory

0.17

 Association

0.17

zheimer

0.15

isease

0.15

AD

0.14

Activations Density 0.004%

terms related to Alzheimer's disease and dementia

No Comments

No Known Activations