INDEX

Explanations

variations of the word "renovate."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

er

-0.16

boards

-0.15

ingly

-0.15

uments

-0.15

aÄĩ

-0.15

board

-0.15

uhn

-0.14

Ø¯Ø§Ø±ÛĮ

-0.14

ddb

-0.14

 fitte

-0.14

POSITIVE LOGITS

egade

0.26

ault

0.23

issance

0.23

owned

0.22

ren

0.21

-ren

0.21

ewed

0.20

ormal

0.20

acimiento

0.19

ren

0.19

Activations Density 0.011%

variations of the word "renovate."

No Comments

No Known Activations

variations of the word "renovate."

No Comments

No Known Activations