INDEX

Explanations

information about hotel features and amenities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

vette

-0.15

ogi

-0.15

 Lust

-0.15

ystore

-0.15

 thrott

-0.14

itto

-0.14

 Strom

-0.14

elda

-0.14

tek

-0.14

à¸Ľà¸£à¸°à¸Īà¸³

-0.14

POSITIVE LOGITS

 guest

0.23

 facilities

0.22

 guests

0.21

 Guests

0.21

guest

0.21

 Facilities

0.20

 Guest

0.20

 modern

0.19

Guest

0.18

amen

0.18

Activations Density 0.062%

information about hotel features and amenities

No Comments

No Known Activations