INDEX

Explanations

programming-related keywords and properties

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ocha

-0.18

ndo

-0.18

odo

-0.15

ä¼į

-0.14

 Thur

-0.14

 InitializeComponent

-0.14

odash

-0.14

ãĥĲãĤ¹

-0.14

uild

-0.13

POSITIVE LOGITS

 strong

0.34

 retain

0.29

strong

0.28

-strong

0.27

nonatomic

0.26

Strong

0.24

 nonatomic

0.24

 copy

0.24

 Strong

0.24

 weak

0.24

Activations Density 0.002%

programming-related keywords and properties

No Comments

No Known Activations

programming-related keywords and properties

No Comments

No Known Activations