INDEX

Explanations

discussions related to programming and coding challenges

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

.scalablytyped

-0.17

Woj

-0.15

CDN

-0.14

Anne

-0.14

README

-0.14

/kg

-0.13

erguson

-0.13

itarian

-0.13

olut

-0.13

 pixmap

-0.13

POSITIVE LOGITS

 Python

0.37

 python

0.34

 Java

0.34

python

0.33

 java

0.33

Python

0.32

 Ruby

0.30

-python

0.29

Java

0.29

ruby

0.29

Activations Density 0.578%

discussions related to programming and coding challenges

No Comments

No Known Activations