INDEX

Explanations

variations of the word "scooter."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

nage

-0.19

nonnull

-0.16

ÑĤÑĢÐ¾

-0.14

ãģĦãĤĭ

-0.14

zel

-0.14

nings

-0.14

 Dwight

-0.14

Won

-0.14

andom

-0.14

acht

-0.14

POSITIVE LOGITS

oters

0.29

oby

0.28

oter

0.25

oped

0.25

ffield

0.23

oping

0.23

ops

0.22

oting

0.21

field

0.21

oop

0.20

Activations Density 0.003%

variations of the word "scooter."

No Comments

No Known Activations