INDEX

Explanations

layout and style properties in code related to UI/UX design

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

uluk

-0.16

acos

-0.14

 Overnight

-0.14

ostel

-0.14

 Gale

-0.13

Low

-0.13

den

-0.13

castle

-0.13

 switch

-0.13

adm

-0.13

POSITIVE LOGITS

atest

0.20

ÑĩÐ¸Ð½Ð¸

0.15

kim

0.15

.equ

0.15

ajs

0.14

Accessor

0.14

.openConnection

0.14

-ves

0.14

kim

0.14

kas

0.14

Activations Density 0.022%

layout and style properties in code related to UI/UX design

No Comments

No Known Activations