INDEX

Explanations

instances of the letter 'P' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

park

-0.17

ENSIONS

-0.16

onna

-0.16

eldorf

-0.15

pitch

-0.14

 pioneer

-0.14

ÅŁehir

-0.14

alion

-0.14

éĻµ

-0.14

URY

-0.14

POSITIVE LOGITS

arsed

0.36

arsing

0.32

ersist

0.31

refix

0.29

arsers

0.29

seudo

0.28

kg

0.28

ayload

0.28

artial

0.28

ipeline

0.27

Activations Density 0.041%

instances of the letter 'P' in various contexts

No Comments

No Known Activations