INDEX

Explanations

instances of notable accomplishments or contributions in various contexts

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

@student

-0.19

 {{--<

-0.17

antaged

-0.17

Ð®ÐĽ

-0.16

eniable

-0.16

heck

-0.15

__,__

-0.15

Ø§Ø²Ùĩ

-0.15

åĳĪ

-0.14

iero

-0.14

POSITIVE LOGITS

 include

0.94

 includes

0.79

include

0.76

 Include

0.73

 INCLUDE

0.65

Include

0.61

includes

0.58

 Includes

0.57

.include

0.54

	include

0.54

Activations Density 0.181%

instances of notable accomplishments or contributions in various contexts

No Comments

No Known Activations