INDEX

Explanations

descriptions of the world and its improvement potential

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

istrovstvÃŃ

-0.19

zell

-0.15

 à¤µà¤ķ

-0.14

elik

-0.14

 Affero

-0.14

 Brom

-0.13

NotificationCenter

-0.13

onda

-0.13

(iter

-0.13

alam

-0.13

POSITIVE LOGITS

-wide

0.17

 wide

0.15

 Minute

0.14

 Heller

0.14

 Spinner

0.14

istrate

0.14

 Bent

0.14

anus

0.14

Heb

0.13

ementia

0.13

Activations Density 0.188%

descriptions of the world and its improvement potential

No Comments

No Known Activations