INDEX

Explanations

terms related to Alzheimer's disease and neurodegeneration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Eudicots

-0.16

zan

-0.15

ê²©

-0.15

anka

-0.15

tember

-0.14

 shutter

-0.14

eya

-0.14

æŁĦ

-0.14

emouth

-0.14

Ä©nh

-0.14

POSITIVE LOGITS

amy

0.36

amy

0.32

Amy

0.28

pla

0.26

 Alzheimer

0.26

Amy

0.26

 deposits

0.25

tau

0.25

 fibr

0.23

Tau

0.23

Activations Density 0.008%

terms related to Alzheimer's disease and neurodegeneration

No Comments

No Known Activations