INDEX

Explanations

phrases and concepts related to history and collective memory

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ÎµÎº

-0.17

 Ð·Ð²

-0.15

flows

-0.15

ì²

-0.15

umes

-0.14

 Buch

-0.14

GBT

-0.14

ToDevice

-0.14

apons

-0.13

aday

-0.13

POSITIVE LOGITS

 history

0.29

 History

0.25

istory

0.23

History

0.22

history

0.22

-history

0.21

 HISTORY

0.20

 historia

0.20

(history

0.20

/history

0.20

Activations Density 0.549%

phrases and concepts related to history and collective memory

No Comments

No Known Activations