INDEX

Explanations

brand names associated with retail products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

kou

-0.18

 commod

-0.15

aÅ¼

-0.14

anik

-0.14

hsi

-0.14

ngine

-0.14

å£«

-0.14

 Mour

-0.14

ernel

-0.14

mux

-0.14

POSITIVE LOGITS

 Benton

0.25

 Walton

0.24

 store

0.23

Wal

0.22

 associates

0.22

 Stores

0.21

 Associates

0.21

 stores

0.21

 Walmart

0.20

 Store

0.19

Activations Density 0.083%

brand names associated with retail products

No Comments

No Known Activations