INDEX

Explanations

numerical data and statistics related to healthcare

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Ð°ÑĪÐ°

-0.17

ãĥªãĥ³ãĤ°

-0.16

oven

-0.15

aida

-0.14

orian

-0.14

ohana

-0.14

 Ø¨ÙĪØ§Ø¨Ø©

-0.14

aleigh

-0.14

ÑĥÑĩÐ°

-0.14

åĲĪãĤıãģĽ

-0.13

POSITIVE LOGITS

igma

0.14

.segments

0.13

otropic

0.13

 âĢı

0.13

wie

0.13

 antibiot

0.13

 Brill

0.13

Bry

0.13

amo

0.13

Activations Density 0.001%

numerical data and statistics related to healthcare

No Comments

No Known Activations