INDEX

Explanations

terms related to medical conditions and diagnostics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 anal

-0.18

 hormonal

-0.17

LEASE

-0.16

lero

-0.16

 hormone

-0.16

dys

-0.16

amy

-0.15

 estrogen

-0.15

 insulin

-0.15

 hist

-0.14

POSITIVE LOGITS

Patients

0.25

Clinical

0.24

 Doctors

0.24

Treatment

0.23

Doctors

0.22

 Treatment

0.21

Patient

0.20

Medical

0.20

 Clinical

0.20

FDA

0.20

Activations Density 0.246%

terms related to medical conditions and diagnostics

No Comments

No Known Activations