INDEX

Explanations

references to museums and exhibitions related to cultural identity and history

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 autoc

-0.14

å¿µ

-0.14

 SCSI

-0.14

 litter

-0.13

 Defence

-0.13

 Creed

-0.13

 Hardware

-0.13

 Seks

-0.13

_barrier

-0.13

ìĹ

-0.13

POSITIVE LOGITS

 museum

0.31

 Museum

0.29

 galleries

0.27

 visitor

0.26

 Visitor

0.25

useum

0.25

 gallery

0.22

-gallery

0.22

 programming

0.22

doc

0.22

Activations Density 0.096%

references to museums and exhibitions related to cultural identity and history

No Comments

No Known Activations