INDEX

Explanations

phrases related to personal contributions and roles 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

amed

-0.17

ÐµÑĢÐ¾

-0.14

akra

-0.14

ernaut

-0.14

erdem

-0.14

.fml

-0.14

ero

-0.14

-instance

-0.14

å½Ĵ

-0.14

uner

-0.14

POSITIVE LOGITS

à¥°

0.15

onis

0.14

Bey

0.14

own

0.14

anity

0.13

.IContainer

0.13

 Kling

0.13

åĬ¡

0.13

ften

0.13

.links

0.13

Activations Density 0.096%

phrases related to personal contributions and roles in various contexts

No Comments

No Known Activations