INDEX

Explanations

references to research or academic studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

assin

-0.15

oons

-0.15

alls

-0.15

lut

-0.15

éĹ

-0.15

ally

-0.15

ulas

-0.15

raud

-0.15

als

-0.14

Î¼Î¹Ïĥ

-0.14

POSITIVE LOGITS

 topics

0.31

Topics

0.28

 Topics

0.27

topics

0.26

_topics

0.26

 topic

0.23

topic

0.23

 Topic

0.22

 themes

0.22

_topic

0.22

Activations Density 0.001%

references to research or academic studies

No Comments

No Known Activations