INDEX

Explanations

mentions of the concept of "loved ones."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

è®

-0.16

/INFO

-0.15

kÃ¼

-0.15

ergic

-0.14

issy

-0.14

ic

-0.13

oro

-0.13

hic

-0.13

 defaultMessage

-0.13

icina

-0.13

POSITIVE LOGITS

 ones

0.80

 Ones

0.71

ones

0.59

ONES

0.43

.ones

0.38

-one

0.27

One

0.27

-One

0.25

_One

0.23

One

0.22

Activations Density 0.012%

mentions of the concept of "loved ones."

No Comments

No Known Activations