INDEX

Explanations

references to museums or historical attractions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

tg

-0.15

ISR

-0.14

ovÃ¡ny

-0.13

 Mein

-0.13

 rooft

-0.13

 abst

-0.13

ungal

-0.13

oulos

-0.13

 Notices

-0.13

rug

-0.13

POSITIVE LOGITS

 museum

0.51

 Museum

0.43

 museums

0.42

åįļçī©

0.36

 exhibits

0.34

 Muse

0.33

useum

0.33

 visitor

0.32

 muse

0.31

 Ð¼ÑĥÐ·

0.31

Activations Density 0.234%

references to museums or historical attractions

No Comments

No Known Activations

references to museums or historical attractions

No Comments

No Known Activations