INDEX

Explanations

technical terms and constructs related to programming or software development

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

(nullptr

-0.17

 Breath

-0.16

.xaml

-0.15

 éĸ¢

-0.15

anga

-0.15

aspers

-0.15

	endif

-0.15

ikh

-0.15

.charCodeAt

-0.14

venta

-0.14

POSITIVE LOGITS

 Ruby

0.30

Ruby

0.28

 ruby

0.28

nil

0.27

||=

0.27

rub

0.26

.rb

0.25

gem

0.25

 rescue

0.25

 ActiveRecord

0.24

Activations Density 0.140%

technical terms and constructs related to programming or software development

No Comments

No Known Activations