INDEX

Explanations

names of medical professionals and their credentials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

esen

-0.16

mers

-0.15

acia

-0.15

/extensions

-0.15

ethod

-0.14

atte

-0.14

tur

-0.14

Zuk

-0.14

rup

-0.14

á»¥

-0.14

POSITIVE LOGITS

 Dodd

0.14

fat

0.14

nish

0.14

ertoire

0.14

 Wonderland

0.14

orda

0.14

nam

0.14

Vor

0.14

_NT

0.14

tk

0.13

Activations Density 0.005%

names of medical professionals and their credentials

No Comments

No Known Activations