INDEX

Explanations

phrases and references related to names and naming conventions

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

arta

-0.18

seau

-0.17

umed

-0.17

aversal

-0.16

opath

-0.16

EMPLARY

-0.15

trand

-0.14

 Disclaimer

-0.14

encies

-0.14

ahr

-0.14

POSITIVE LOGITS

 reference

0.31

 named

0.30

reference

0.28

 ÙĨØ³Ø¨Ø©

0.27

named

0.26

 Named

0.26

Reference

0.25

 referencing

0.25

 ÑĩÐµÑģÑĤÑĮ

0.25

 referring

0.24

Activations Density 0.118%

phrases and references related to names and naming conventions

No Comments

No Known Activations