INDEX

Explanations

features related to home amenities and layout

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Chamber

-0.15

azÄĥ

-0.15

.nano

-0.15

 mattress

-0.15

 couch

-0.14

igar

-0.14

ancell

-0.14

 mattresses

-0.14

chg

-0.14

bed

-0.14

POSITIVE LOGITS

 kitchen

0.22

Kitchen

0.22

 Kitchen

0.21

vection

0.19

 Cooking

0.19

Cook

0.18

 island

0.18

 Appliances

0.18

 sink

0.18

 kitchens

0.18

Activations Density 0.112%

features related to home amenities and layout

No Comments

No Known Activations