INDEX

Explanations

expressions of gratitude and conversation themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

.ua

-0.20

lds

-0.17

uros

-0.15

bject

-0.14

ulp

-0.14

Īëĭ¤

-0.14

iture

-0.14

gger

-0.14

oog

-0.14

ourg

-0.14

POSITIVE LOGITS

dem

0.30

mi

0.30

fi

0.28

di

0.27

nu

0.24

mek

0.23

pon

0.23

seh

0.22

tek

0.22

Mi

0.22

Activations Density 0.002%

expressions of gratitude and conversation themes

No Comments

No Known Activations