INDEX

Explanations

terms related to doctors and medical professionals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ted

-0.17

uchi

-0.16

elay

-0.15

Ð¸Ð½Ð¾Ðº

-0.15

igator

-0.15

oplan

-0.14

kÃ³w

-0.14

edd

-0.14

ãģĴ

-0.14

deniz

-0.14

POSITIVE LOGITS

/engine

0.16

ettle

0.16

LinkId

0.16

ë§ģ

0.15

ession

0.15

olland

0.14

Ð¾Ð¿ÑĢÐ¸

0.14

Rut

0.13

EAR

0.13

 Barth

0.13

Activations Density 0.025%

terms related to doctors and medical professionals

No Comments

No Known Activations