INDEX

Explanations

code-related keywords and exceptions 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

akens

-0.15

arry

-0.15

odel

-0.15

asse

-0.14

lio

-0.14

.UIManager

-0.14

 Hayes

-0.14

GetSize

-0.14

áº½

-0.14

 interchange

-0.13

POSITIVE LOGITS

.java

0.50

.scala

0.31

 java

0.29

java

0.26

.class

0.24

 Java

0.23

_java

0.22

.Java

0.22

-java

0.21

.jav

0.20

Activations Density 0.065%

code-related keywords and exceptions in a programming context

No Comments

No Known Activations