INDEX

Explanations

references to technology products and their specifications

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

.scalablytyped

-0.19

marshall

-0.17

 ÚĺØ§ÙĨ

-0.16

EDI

-0.15

erals

-0.15

orsk

-0.14

ostel

-0.14

 ÙĨÙģ

-0.14

jours

-0.14

AsyncResult

-0.14

POSITIVE LOGITS

 Vega

0.28

Zen

0.26

 Ryzen

0.26

 Radeon

0.25

RX

0.22

RD

0.22

 Raven

0.22

ry

0.21

zen

0.21

 Fury

0.21

Activations Density 0.004%

references to technology products and their specifications

No Comments

No Known Activations