INDEX

Explanations

medical terms related to strokes and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

addock

-0.17

ãĥ¼ãĥĢ

-0.15

ensch

-0.15

_pitch

-0.14

ogh

-0.14

blem

-0.14

seau

-0.14

emas

-0.14

ÄĽti

-0.14

illes

-0.14

POSITIVE LOGITS

 stroke

0.35

 Stroke

0.35

Stroke

0.30

stroke

0.29

 strokes

0.25

.stroke

0.22

-strokes

0.20

 brain

0.20

 Brain

0.18

 stro

0.17

Activations Density 0.041%

medical terms related to strokes and their implications

No Comments

No Known Activations