INDEX

Explanations

geographic names and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

edir

-0.14

avax

-0.14

rox

-0.14

iasi

-0.14

ledon

-0.14

uye

-0.14

_PIXEL

-0.14

DRV

-0.13

quito

-0.13

berger

-0.13

POSITIVE LOGITS

 à¸Ľà¸£à¸°à¹Ģà¸Ĺà¸¨

0.22

 California

0.21

 Arizona

0.20

 Florida

0.20

 Pennsylvania

0.18

 Texas

0.18

 Oregon

0.18

 Georgia

0.17

 Virginia

0.17

 Massachusetts

0.17

Activations Density 0.138%

geographic names and locations

No Comments

No Known Activations