INDEX

Explanations

negations or words indicating the absence of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

uki

-0.15

allis

-0.15

OperationException

-0.15

FindObject

-0.15

bye

-0.15

TestCategory

-0.15

cessive

-0.14

esModule

-0.14

 "-//

-0.14

å³°

-0.14

POSITIVE LOGITS

 only

0.27

 just

0.21

 least

0.21

 unlike

0.19

 merely

0.19

ches

0.18

 hanya

0.18

 chá»ī

0.18

 ÑĤÐ¾Ð»ÑĮÐºÐ¾

0.17

 tylko

0.17

Activations Density 0.038%

negations or words indicating the absence of something

No Comments

No Known Activations