INDEX

Explanations

medical professionals and their specialties

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ally

-0.16

orer

-0.16

ellas

-0.15

 airport

-0.15

 Sonia

-0.15

OST

-0.14

 ÑĢÐ¾Ð»ÑĮ

-0.14

onen

-0.13

 stringBuffer

-0.13

dana

-0.13

POSITIVE LOGITS

boom

0.15

ì§ĢëıĦ

0.15

Äįka

0.15

 Levin

0.14

 Ø¯Ø±Ø³

0.14

ÐºÐ¾Ð¿

0.14

uxt

0.14

ached

0.14

prise

0.13

.Generated

0.13

Activations Density 0.010%

medical professionals and their specialties

No Comments

No Known Activations