INDEX

Explanations

phrases related to hotel amenities and features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

AMERA

-0.16

ycastle

-0.15

stants

-0.15

 kelim

-0.15

Äįe

-0.15

ÑĩÐµ

-0.15

Ìģc

-0.14

ijkstra

-0.14

VML

-0.14

inqu

-0.14

POSITIVE LOGITS

pet

0.22

 Extended

0.21

extended

0.21

pet

0.20

Extended

0.19

 Hampton

0.19

 Candle

0.18

 Embassy

0.18

 extended

0.18

 traveler

0.18

Activations Density 0.066%

phrases related to hotel amenities and features

No Comments

No Known Activations