INDEX

Explanations

references to influential figures or entities in specific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 behaviors

-0.26

 defense

-0.21

 neighborhoods

-0.20

 modeling

-0.20

 modeled

-0.20

defense

-0.20

neighbor

-0.19

 Defense

-0.19

 fueled

-0.19

Defense

-0.19

POSITIVE LOGITS

 page

0.23

PAGE

0.21

 connexion

0.20

page

0.20

 PAGE

0.20

 Page

0.20

-page

0.19

Page

0.18

_page

0.17

.page

0.17

Activations Density 0.005%

references to influential figures or entities in specific contexts

No Comments

No Known Activations