INDEX

Explanations

code-related keywords and decorators 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

à¥Ģà¤®

-0.14

 Berk

-0.14

agini

-0.14

 MÃľ

-0.14

vas

-0.14

ylie

-0.13

 Screw

-0.13

undle

-0.13

POSITIVE LOGITS

property

0.28

staticmethod

0.28

classmethod

0.27

 property

0.24

.setter

0.23

 decorator

0.20

 Decor

0.19

 decor

0.19

-property

0.19

 Property

0.18

Activations Density 0.007%

code-related keywords and decorators in a programming context

No Comments

No Known Activations