INDEX

Explanations

numerical values and references to measurable quantities

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

âĢ¦↵↵↵

-0.25

Ã¡bado

-0.15

-INFRINGEMENT

-0.14

orest

-0.13

ï¼ļ↵

-0.13

Winvalid

-0.12

 Uncategorized

-0.12

.liferay

-0.12

(íģ¬ê¸°

-0.12

ï¼Ł↵↵

-0.12

POSITIVE LOGITS

 bordel

0.12

ova

0.12

Slf

0.12

 Stadium

0.12

 nouve

0.11

uteur

0.11

 à¹Ĩ

0.11

 scarcely

0.11

quot

0.11

OTO

0.10

Activations Density 0.064%

numerical values and references to measurable quantities

No Comments

No Known Activations