INDEX

Explanations

verbs related to medical conditions and patient status

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

Ŀ

-0.18

ivor

-0.15

Ð¼Ð°Ñħ

-0.15

uggage

-0.15

ÙĬÙĥÙĬ

-0.15

enties

-0.14

iquÃ©

-0.14

xon

-0.14

odon

-0.13

nze

-0.13

POSITIVE LOGITS

 prescribed

0.26

 admitted

0.22

 diag

0.20

 continent

0.19

 fitted

0.18

 diagon

0.18

 operated

0.17

 placed

0.17

 wheelchair

0.17

diag

0.17

Activations Density 0.111%

verbs related to medical conditions and patient status

No Comments

No Known Activations