INDEX

Explanations

words that indicate legal or formal decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

gres

-0.15

ylland

-0.15

 Loose

-0.15

entin

-0.14

 Mein

-0.14

ocha

-0.14

CCI

-0.14

pee

-0.14

 vain

-0.13

POSITIVE LOGITS

acey

0.16

obus

0.16

bron

0.16

ardon

0.15

unday

0.15

YD

0.15

igham

0.15

à¹ģà¸£à¸ģ

0.14

utomation

0.14

opers

0.14

Activations Density 0.011%

words that indicate legal or formal decision-making processes

No Comments

No Known Activations