INDEX

Explanations

terms and phrases associated with diagnostic methods and results in clinical specimens

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

odb

-0.15

 wound

-0.15

cai

-0.14

otland

-0.14

Ø±Ø¨

-0.14

Æ°á»Ŀn

-0.14

Ð±Ð°Ð²

-0.14

 kraje

-0.14

ooth

-0.14

statt

-0.14

POSITIVE LOGITS

 lymph

0.28

 blast

0.28

 blasts

0.27

 leukemia

0.26

AML

0.25

CLL

0.25

rel

0.24

NHL

0.24

 bone

0.23

 marrow

0.23

Activations Density 0.027%

terms and phrases associated with diagnostic methods and results in clinical specimens

No Comments

No Known Activations