INDEX

Explanations

specific phrases related to the number two and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

two

-0.18

ä¸¤ä¸ª

-0.16

 twee

-0.16

äºĮäºº

-0.16

 beiden

-0.15

vat

-0.15

hai

-0.15

Nos

-0.14

 both

-0.14

inkle

-0.14

POSITIVE LOGITS

-One

0.18

mÃ©na

0.18

vier

0.17

iences

0.17

ä¹ĭä¸Ģ

0.17

ToOne

0.16

 birden

0.16

igne

0.15

åĲĮæĹ¶

0.15

fram

0.15

Activations Density 0.107%

specific phrases related to the number two and its variations

No Comments

No Known Activations