INDEX

Explanations

references to teaching and educational tools in the medical field

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Municipal

-0.15

iaux

-0.14

CodeGen

-0.14

shm

-0.14

arg

-0.14

ersed

-0.14

ocre

-0.14

RITE

-0.14

rim

-0.14

iron

-0.13

POSITIVE LOGITS

gross

0.30

 gross

0.30

 Gross

0.27

 anatomy

0.26

cad

0.26

 Anatomy

0.23

 hist

0.22

 organs

0.21

 human

0.21

 muscles

0.20

Activations Density 0.043%

references to teaching and educational tools in the medical field

No Comments

No Known Activations