INDEX

Explanations

phrases indicating future discussions or planned actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

raph

-0.14

Ø§ÙģØªÙĩ

-0.14

argas

-0.14

 taxing

-0.14

 Colonial

-0.14

 ÐĶÐ¾Ð±

-0.13

aeda

-0.13

 Giov

-0.13

 svÄĽ

-0.13

 Leban

-0.13

POSITIVE LOGITS

 cover

0.29

 covers

0.28

 covering

0.26

 discuss

0.26

cover

0.25

 briefly

0.25

 covered

0.24

 talk

0.24

 sharing

0.23

 discusses

0.22

Activations Density 0.067%

phrases indicating future discussions or planned actions

No Comments

No Known Activations