INDEX

Explanations

programming syntax and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ajs

-0.18

.pretty

-0.15

Misc

-0.15

æłª

-0.15

@{$

-0.14

ooter

-0.14

muj

-0.14

@$

-0.14

_misc

-0.14

#__

-0.14

POSITIVE LOGITS

 class

0.28

class

0.26

use

0.25

 abstract

0.24

abstract

0.24

use

0.22

	class

0.21

ini

0.20

 Abstract

0.20

 Class

0.19

Activations Density 0.005%

programming syntax and structure

No Comments

No Known Activations