INDEX

Explanations

programming-related concepts and keywords

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

aylor

-0.14

.MixedReality

-0.13

>{!!

-0.13

>Please

-0.12

iams

-0.12

æŁĦ

-0.11

ofi

-0.11

Ã¤nn

-0.11

Ã£i

-0.11

ervisor

-0.11

POSITIVE LOGITS

 class

1.27

class

1.07

 Class

1.03

-class

0.99

 classes

0.96

Class

0.93

_class

0.92

 ÐºÐ»Ð°ÑģÑģ

0.90

 classe

0.89

	class

0.88

Activations Density 0.151%

programming-related concepts and keywords

No Comments

No Known Activations