INDEX

Explanations

code and technical terms related to Java programming

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

tap

-0.17

vvm

-0.16

Tap

-0.14

lit

-0.14

 Stark

-0.14

.getDrawable

-0.14

_flutter

-0.14

.detectChanges

-0.14

.setLayoutParams

-0.14

GuidId

-0.14

POSITIVE LOGITS

 Swing

0.31

 swing

0.27

 Component

0.27

Component

0.26

 javax

0.25

swing

0.24

 component

0.24

.swing

0.23

-component

0.23

 JPanel

0.23

Activations Density 0.042%

code and technical terms related to Java programming

No Comments

No Known Activations