INDEX

Explanations

keywords indicating participation and interaction in various activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ouble

-0.16

sci

-0.15

olumn

-0.15

åĿĲ

-0.15

 authDomain

-0.15

omon

-0.15

ighted

-0.15

edik

-0.14

itÃ©s

-0.14

ansson

-0.14

POSITIVE LOGITS

uzzi

0.17

warts

0.15

Î¸Ïħ

0.15

aniu

0.15

 Design

0.15

icious

0.14

:animated

0.14

la

0.14

uges

0.14

Activations Density 0.011%

keywords indicating participation and interaction in various activities

No Comments

No Known Activations