INDEX

Explanations

formatting marks or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

¶Į

-0.19

Ø±Ùĩ

-0.17

lek

-0.16

tant

-0.15

 âĨĴ

-0.14

spor

-0.14

------------------------------------------------------------------------------------------------

-0.14

 --->

-0.14

-------------</

-0.14

><?

-0.14

POSITIVE LOGITS

==============

0.29

=============

0.28

============

0.27

====

0.26

========

0.25

===========

0.25

===

0.25

===============

0.25

================================

0.24

==========

0.24

Activations Density 0.014%

formatting marks or symbols

No Comments

No Known Activations