INDEX

Explanations

references to decision-making processes and the concept of decisions in general

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

pei

-0.18

ampie

-0.17

-0.16

ture

-0.16

ugi

-0.15

legen

-0.15

/Dk

-0.15

ilden

-0.15

riere

-0.15

ersen

-0.15

POSITIVE LOGITS

-making

0.31

al

0.30

 makers

0.30

-makers

0.29

-maker

0.28

 maker

0.28

 Maker

0.27

 taken

0.26

makers

0.24

Maker

0.24

Activations Density 0.048%

references to decision-making processes and the concept of decisions in general

No Comments

No Known Activations