INDEX

Explanations

programming-related terms and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 serialVersionUID

-0.18

SupportedContent

-0.15

alim

-0.15

[][]

-0.15

coon

-0.14

zÄ±

-0.14

/******/

-0.14

>>()

-0.14

[]=$

-0.14

.java

-0.14

POSITIVE LOGITS

::

0.38

_ptr

0.26

 const

0.26

::~

0.26

0.25

Traits

0.24

Ptr

0.23

&&

0.23

SharedPtr

0.23

::

0.21

Activations Density 0.033%

programming-related terms and functions

No Comments

No Known Activations