INDEX

Explanations

references to stores and availability of products within a retail context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Shipping

-0.15

 Customers

-0.15

Shipping

-0.15

 SHIPPING

-0.14

ymm

-0.14

 Restaurants

-0.14

 Ordering

-0.14

ÏĦÎµÏħ

-0.14

 Customer

-0.14

Customer

-0.13

POSITIVE LOGITS

 store

0.36

 story

0.32

 stories

0.30

em

0.30

 outlet

0.28

 stores

0.28

 mart

0.27

_story

0.27

Emp

0.26

 outlets

0.26

Activations Density 0.101%

references to stores and availability of products within a retail context

No Comments

No Known Activations