INDEX

Explanations

medical professions and their associated expertise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 legit

-0.16

NSE

-0.15

ÐºÐ°Ð²

-0.14

 íĻĺ

-0.14

itler

-0.14

anian

-0.14

ertz

-0.14

Chron

-0.14

onian

-0.14

DebugEnabled

-0.13

POSITIVE LOGITS

 Apollo

0.24

Apollo

0.24

 Consultant

0.21

apollo

0.21

Ay

0.20

AI

0.20

ICON

0.19

ay

0.19

OP

0.18

 Lady

0.18

Activations Density 0.116%

medical professions and their associated expertise

No Comments

No Known Activations