INDEX

Explanations

mentions of "Star" and related terms linked to the "Star Wars" franchise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ierz

-0.17

kaz

-0.17

gens

-0.16

ymous

-0.16

adesh

-0.16

estro

-0.16

yses

-0.16

emes

-0.16

erp

-0.15

Zuk

-0.15

POSITIVE LOGITS

ry

0.27

kest

0.24

vation

0.24

/star

0.24

bucks

0.23

ved

0.23

ving

0.21

 Star

0.21

 Wars

0.21

fish

0.21

Activations Density 0.016%

mentions of "Star" and related terms linked to the "Star Wars" franchise

No Comments

No Known Activations