INDEX

Explanations

references to the concept of "home."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

neau

-0.18

edImage

-0.16

naire

-0.15

maz

-0.15

etable

-0.15

ìĿĦ

-0.15

-Ray

-0.15

æĸĻ

-0.14

asel

-0.14

eries

-0.14

POSITIVE LOGITS

grown

0.26

brew

0.24

opathic

0.23

coming

0.23

omorphic

0.22

opathy

0.22

lessness

0.22

 grown

0.21

 Alone

0.21

less

0.20

Activations Density 0.033%

references to the concept of "home."

No Comments

No Known Activations