INDEX

Explanations

phrases concerning informed decision-making and personal agency

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

Ð·Ð°Ð±

-0.20

igue

-0.18

orda

-0.15

ç§

-0.15

Ìĥ

-0.14

ancock

-0.14

 configurable

-0.14

áº¡p

-0.14

cott

-0.14

POSITIVE LOGITS

 informed

0.37

 educated

0.32

 choices

0.26

 snap

0.25

educated

0.25

-educated

0.24

 wise

0.23

 sound

0.23

 smart

0.22

 intelligent

0.22

Activations Density 0.066%

phrases concerning informed decision-making and personal agency

No Comments

No Known Activations