INDEX

Explanations

numerical information related to statistics and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ä¹İ

-0.17

iÃ³

-0.16

jes

-0.15

esti

-0.15

.gwt

-0.14

jew

-0.14

ìĭŃ

-0.14

uum

-0.14

ocrat

-0.13

ruc

-0.13

POSITIVE LOGITS

hiro

0.19

apÄ±

0.17

opher

0.16

à¤¼

0.16

athon

0.15

Ã¡bado

0.15

ification

0.15

bru

0.15

BRA

0.15

Activations Density 0.134%

numerical information related to statistics and measurements

No Comments

No Known Activations