INDEX

Explanations

intensifiers that amplify the significance or impact of statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 completely

-0.18

 Ð¿Ð¾Ð»Ð½Ð¾ÑģÑĤÑĮÑİ

-0.16

idor

-0.15

 entirely

-0.15

enger

-0.15

bach

-0.15

 really

-0.14

 faced

-0.14

 totally

-0.14

unci

-0.14

POSITIVE LOGITS

æĿ

0.20

 outnumber

0.17

 different

0.16

ä¸įåĲĮçļĦ

0.16

etooth

0.15

 influenced

0.15

 affected

0.15

 impacted

0.14

 Ð·Ð°Ð²Ð¸ÑģÐ¸ÑĤ

0.14

ham

0.14

Activations Density 0.088%

intensifiers that amplify the significance or impact of statements

No Comments

No Known Activations