INDEX

Explanations

mentions of accommodations and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 selectors

-0.18

kah

-0.15

ahas

-0.14

è£ķ

-0.14

 selector

-0.14

McG

-0.14

 AÄŁustos

-0.14

æľ¬

-0.14

 Ricardo

-0.13

Resume

-0.13

POSITIVE LOGITS

otel

0.20

 hotel

0.20

bed

0.19

 Hotel

0.17

 Scalars

0.16

 chains

0.16

 beds

0.16

 stay

0.16

 rooms

0.15

 Stay

0.15

Activations Density 0.219%

mentions of accommodations and their attributes

No Comments

No Known Activations