INDEX

Explanations

expressions of curiosity and interest

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

awah

-0.16

quan

-0.15

arry

-0.14

à¸Ńà¸ĩà¸Īà¸²à¸ģ

-0.14

 DÃ¼n

-0.14

ols

-0.14

aph

-0.14

aware

-0.14

ams

-0.14

Aware

-0.14

POSITIVE LOGITS

 curiosity

0.47

 curious

0.37

 interest

0.34

 Interest

0.30

interest

0.29

 ê¶ģê¸Ī

0.28

Interest

0.28

 intrigue

0.27

-interest

0.27

 intrigued

0.27

Activations Density 0.170%

expressions of curiosity and interest

No Comments

No Known Activations