INDEX

Explanations

instances of objects related to coding or programming terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

æĢĿãģĦ

-0.15

.isUser

-0.15

aise

-0.15

lenÃŃ

-0.15

 ÙĩØ´

-0.14

gregator

-0.14

)((((

-0.14

Lon

-0.14

erton

-0.14

ogg

-0.14

POSITIVE LOGITS

HomeAsUp

0.15

Ð¾Ð±Ð¾Ð²

0.14

Ð²Ð¾ÑĢ

0.14

col

0.14

à¥ģà¤¡

0.14

 expend

0.13

cms

0.13

 Happ

0.13

uml

0.13

pat

0.13

Activations Density 0.001%

instances of objects related to coding or programming terminology

No Comments

No Known Activations