INDEX

Explanations

references to data handling and operations in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

noinspection

-0.15

Î¼Î¹

-0.15

abs

-0.14

URE

-0.14

ugged

-0.14

 commission

-0.14

ark

-0.13

weis

-0.13

etal

-0.13

uide

-0.13

POSITIVE LOGITS

->

0.57

->

0.38

->_

0.30

()->

0.29

::

0.27

->↵

0.26

_->

0.25

-&

0.25

âĨĴ

0.24

->___

0.23

Activations Density 0.029%

references to data handling and operations in a programming context

No Comments

No Known Activations