INDEX

Explanations

references to locations or geographic areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

/welcome

-0.17

ioc

-0.15

 Crossing

-0.15

alom

-0.15

par

-0.15

amar

-0.14

ancock

-0.14

Ð¸Ñĩ

-0.14

inger

-0.14

inium

-0.14

POSITIVE LOGITS

/Dk

0.20

0.17

enza

0.16

vak

0.15

Gratis

0.15

ATUS

0.15

 thÃŃ

0.14

 Assets

0.14

Î»Ïİ

0.14

chu

0.14

Activations Density 0.222%

references to locations or geographic areas

No Comments

No Known Activations