INDEX

Explanations

variations of the word "polish" and related terms, indicating an interest in processes or products that enhance shine or cleanliness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ilet

-0.17

dit

-0.16

amarin

-0.16

uja

-0.15

 Thornton

-0.15

ecute

-0.15

duino

-0.14

abet

-0.14

Ã©nÃ©

-0.14

zk

-0.14

POSITIVE LOGITS

ocoder

0.17

etta

0.15

rÃ³d

0.14

ioso

0.14

ëª°

0.14

 UNUSED

0.13

berger

0.13

andes

0.13

éĿ

0.13

 Äĳiá»ĥn

0.13

Activations Density 0.009%

variations of the word "polish" and related terms, indicating an interest in processes or products that enhance shine or cleanliness

No Comments

No Known Activations