INDEX

Explanations

references to upgrades and improvements related to physical structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Ð±Ð¾ÑĤ

-0.17

inois

-0.16

eec

-0.15

imeo

-0.15

xad

-0.14

adors

-0.14

gom

-0.14

 Beit

-0.13

iado

-0.13

sj

-0.13

POSITIVE LOGITS

ble

0.33

 seats

0.27

Ble

0.26

 tier

0.26

 rows

0.25

 reserved

0.25

reserved

0.24

ble

0.24

 balcony

0.24

 Tier

0.23

Activations Density 0.059%

references to upgrades and improvements related to physical structures

No Comments

No Known Activations