INDEX

Explanations

descriptors related to products and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ãĤ½ãĥ³

-0.17

ãĤ©

-0.15

.scalablytyped

-0.14

à¤¡à¤°

-0.14

ehir

-0.14

Ä¢

-0.14

azi

-0.14

ãĥĲãĥ¼

-0.13

 otom

-0.13

Lifecycle

-0.13

POSITIVE LOGITS

 bestselling

0.16

 pure

0.15

QualifiedName

0.13

 prest

0.13

ivery

0.13

åĩĨ

0.13

 Moff

0.13

 Weird

0.13

 Pure

0.13

readcr

0.13

Activations Density 0.084%

descriptors related to products and their features

No Comments

No Known Activations