INDEX

Explanations

references to academic research and discussions of university-related issues

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

 âĢ¦

-0.27

...

-0.24

 ..."

-0.21

↵

-0.20

..

-0.20

..

-0.19

ÂŃ

-0.18

...

-0.18

..."

-0.18

âĢ¦

-0.17

POSITIVE LOGITS

',...↵

0.18

ibs

0.16

-----------*/↵

0.15

,");↵

0.15

boa

0.15

 -/↵

0.14

vae

0.14

ilan

0.14

bler

0.14

 |--------------------------------------------------------------------------↵

0.14

Activations Density 0.067%

references to academic research and discussions of university-related issues

No Comments

No Known Activations