INDEX

Explanations

words and phrases related to unity, leadership, and organization structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

rus

-0.17

/fw

-0.16

outine

-0.15

æľĭ

-0.14

aze

-0.14

dev

-0.14

rze

-0.13

gend

-0.13

ibu

-0.13

ginas

-0.13

POSITIVE LOGITS

ÐµÐ´Ð¸

0.17

istrovstvÃŃ

0.17

oya

0.16

<source

0.15

/shared

0.15

elik

0.15

GPC

0.14

arpa

0.14

born

0.14

esModule

0.14

Activations Density 0.157%

words and phrases related to unity, leadership, and organization structure

No Comments

No Known Activations