INDEX

Explanations

requests for additional information or learning opportunities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

dn

-0.15

 Fried

-0.15

hood

-0.15

ford

-0.15

 waste

-0.14

ft

-0.14

less

-0.14

 Stefan

-0.14

isko

-0.14

esh

-0.13

POSITIVE LOGITS

 about

0.29

about

0.23

 tentang

0.23

 ABOUT

0.22

 Ø¹ÙĨÙĩ

0.22

_about

0.22

 About

0.19

About

0.19

.about

0.18

-about

0.18

Activations Density 0.024%

requests for additional information or learning opportunities

No Comments

No Known Activations