INDEX

Explanations

references to celebrating LGBTQ+ pride and community support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ÑĤÐ°Ð»

-0.17

(gcf

-0.16

 HOLDER

-0.16

SEE

-0.15

 ëħ

-0.15

zag

-0.14

HOLDER

-0.14

.generic

-0.14

oku

-0.14

 Carp

-0.14

POSITIVE LOGITS

 wear

0.38

 wearing

0.37

 wears

0.36

 Wear

0.35

 wore

0.34

 worn

0.33

 rock

0.31

 rocking

0.30

 wearer

0.29

 sport

0.28

Activations Density 0.112%

references to celebrating LGBTQ+ pride and community support

No Comments

No Known Activations