INDEX

Explanations

mentions of food-related concepts and accommodations in reviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ru

-0.17

 Fever

-0.15

dao

-0.15

 sonu

-0.15

witch

-0.14

 Disposable

-0.14

GRP

-0.14

ilver

-0.14

 segreg

-0.14

itra

-0.14

POSITIVE LOGITS

 breakfast

0.26

-break

0.25

break

0.24

Break

0.24

 Breakfast

0.23

 BREAK

0.21

bre

0.21

 Continental

0.19

_BREAK

0.18

 continental

0.18

Activations Density 0.007%

mentions of food-related concepts and accommodations in reviews

No Comments

No Known Activations