INDEX

Explanations

numerical values and their associated context in medical and scientific data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anga

-0.15

arters

-0.15

ÑĥÑĢÑĭ

-0.15

Ø§ÙĪÛĮØ±

-0.15

ksen

-0.14

opensource

-0.14

erge

-0.14

 pressure

-0.14

phy

-0.14

trys

-0.13

POSITIVE LOGITS

ayi

0.15

uentes

0.15

kov

0.14

 Relay

0.14

elay

0.14

uis

0.13

IFY

0.13

issen

0.13

acom

0.13

Disposition

0.13

Activations Density 0.048%

numerical values and their associated context in medical and scientific data

No Comments

No Known Activations