INDEX

Explanations

references to promotional products and branding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

igon

-0.15

 pseud

-0.14

iku

-0.14

aller

-0.14

actors

-0.14

 Liberation

-0.14

ä¸ģ

-0.13

ãĥ³ãĥĹ

-0.13

á»©ng

-0.13

ilon

-0.13

POSITIVE LOGITS

 Prom

0.30

 promotional

0.29

 promo

0.28

Prom

0.27

 Promo

0.25

prom

0.25

 Promotion

0.25

 promotion

0.24

 promote

0.23

 prom

0.23

Activations Density 0.038%

references to promotional products and branding

No Comments

No Known Activations