INDEX

Explanations

references to the "Game of Thrones" franchise and associated elements

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

Å¡tÃŃ

-0.17

dle

-0.16

idge

-0.16

ILLE

-0.15

.si

-0.15

ecz

-0.15

ÐºÑĥÑĢ

-0.15

HING

-0.15

erty

-0.14

ids

-0.14

POSITIVE LOGITS

rones

0.27

th

0.26

 Thrones

0.23

 drones

0.20

 throne

0.18

rone

0.17

 drone

0.17

 chairs

0.17

 Chairs

0.16

 crow

0.16

Activations Density 0.008%

references to the "Game of Thrones" franchise and associated elements

No Comments

No Known Activations