INDEX

Explanations

historical figures and important dates

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

 gratuites

-0.16

 ç²¾

-0.15

 Welch

-0.15

egot

-0.15

 gratuiti

-0.14

 maiden

-0.14

ProgressHUD

-0.14

Cancelable

-0.14

POSITIVE LOGITS

 Ember

0.26

Rog

0.25

Vig

0.24

 Sole

0.24

 Palm

0.23

 Pent

0.22

 vigil

0.22

fe

0.22

 octave

0.22

 Proper

0.21

Activations Density 0.050%

historical figures and important dates

No Comments

No Known Activations