INDEX

Explanations

references to historical architecture and monuments

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

 Alman

-0.16

rary

-0.15

al

-0.15

 Murdoch

-0.15

sm

-0.14

 Terrace

-0.14

requencies

-0.13

åį°

-0.13

optim

-0.13

erland

-0.13

POSITIVE LOGITS

 preservation

0.22

 Preservation

0.20

 histor

0.18

 Historic

0.18

 Architect

0.16

 heritage

0.16

 endangered

0.16

 historic

0.15

 listing

0.15

 architectural

0.15

Activations Density 0.095%

references to historical architecture and monuments

No Comments

No Known Activations