INDEX

Explanations

geographical locations and addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 seins

-0.17

adu

-0.16

iggs

-0.16

æŁĵ

-0.15

Mev

-0.15

chten

-0.15

arkan

-0.14

olina

-0.14

bstract

-0.14

esson

-0.14

POSITIVE LOGITS

Kew

0.27

 Superior

0.25

 Mack

0.23

 Peninsula

0.22

 Michigan

0.21

 Alger

0.21

UP

0.21

Ish

0.20

 Copper

0.20

 Nico

0.19

Activations Density 0.036%

geographical locations and addresses

No Comments

No Known Activations