INDEX

Explanations

references to informal, DIY, and amateur activities in various sectors

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

 ÐµÑģÑĤÑĮ

-0.16

inou

-0.16

agrams

-0.14

 Crowley

-0.14

Glo

-0.14

AccessType

-0.14

gid

-0.14

 Marble

-0.14

lassen

-0.13

 esac

-0.13

POSITIVE LOGITS

rescia

0.17

ogany

0.15

 Amateur

0.14

 amateur

0.14

 elderly

0.14

Orr

0.14

umann

0.14

alnÄ±z

0.14

vore

0.14

ront

0.13

Activations Density 0.124%

references to informal, DIY, and amateur activities in various sectors

No Comments

No Known Activations