INDEX

Explanations

mentions of healthcare professionals and their roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ties

-0.15

geber

-0.15

bourg

-0.15

sse

-0.14

punkt

-0.14

aju

-0.14

/INFO

-0.14

Ø®Ø§Ø¨

-0.14

emony

-0.14

uchi

-0.14

POSITIVE LOGITS

ate

0.32

/ph

0.27

 prescribing

0.24

 assistant

0.23

 offices

0.22

 treating

0.21

 prescribed

0.21

 assistants

0.21

/engine

0.20

-pres

0.20

Activations Density 0.039%

mentions of healthcare professionals and their roles

No Comments

No Known Activations