INDEX

Explanations

terms related to software development practices and architecture

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

porte

-0.19

éľŀ

-0.17

ndef

-0.15

.Compiler

-0.14

eldorf

-0.14

 áº¢nh

-0.14

 IonicModule

-0.14

 Dreams

-0.14

BaseContext

-0.14

-disable

-0.13

POSITIVE LOGITS

 patterns

0.25

 Patterns

0.24

 separation

0.23

 Design

0.23

DDD

0.23

 design

0.23

 pattern

0.23

 Separ

0.22

ref

0.22

SOL

0.22

Activations Density 0.124%

terms related to software development practices and architecture

No Comments

No Known Activations