INDEX

Explanations

phrases that highlight the amenities and features of a location or establishment

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

ogne

-0.16

izzo

-0.15

dit

-0.15

cretion

-0.14

anel

-0.14

Ð²Ð¸ÑĩÐ°Ð¹

-0.14

mbH

-0.14

 vÃ½Å¡e

-0.14

 Identified

-0.14

upo

-0.14

POSITIVE LOGITS

 highlight

0.24

 dÃ©cor

0.21

 decor

0.21

 emphasis

0.20

 focal

0.20

 setting

0.19

 piÃ¨

0.19

 view

0.18

 vibe

0.18

 layout

0.17

Activations Density 0.114%

phrases that highlight the amenities and features of a location or establishment

No Comments

No Known Activations

phrases that highlight the amenities and features of a location or establishment

No Comments

No Known Activations