INDEX

Explanations

terms and mentions related to nursing and healthcare professionals

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

Ã«n

-0.17

ifer

-0.16

lush

-0.15

ymous

-0.15

LAY

-0.15

rine

-0.15

 annonces

-0.15

loh

-0.14

ilet

-0.14

opy

-0.14

POSITIVE LOGITS

maid

0.33

maids

0.29

 practitioner

0.20

 Pract

0.19

Mid

0.18

 shortage

0.18

Mid

0.18

urst

0.17

 shortages

0.16

mid

0.16

Activations Density 0.016%

terms and mentions related to nursing and healthcare professionals

No Comments

No Known Activations