INDEX

Explanations

technical terms and structures related to computer graphics or programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

SupportedContent

-0.18

SystemService

-0.15

>NN

-0.15

[=[

-0.14

|#

-0.14

[/

-0.14

alim

-0.14

javax

-0.13

 [...]

-0.13

ynamo

-0.13

POSITIVE LOGITS

::

0.48

0.38

 const

0.36

::~

0.35

Ptr

0.34

&)

0.32

&,

0.32

::_

0.31

0.30

_ptr

0.29

Activations Density 0.033%

technical terms and structures related to computer graphics or programming

No Comments

No Known Activations