INDEX

Explanations

phrases that indicate increasing amounts or degrees 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

à¸Ľà¸£à¸°à¸Īà¸³

-0.17

elt

-0.16

Å¡k

-0.16

Ø³Ø§ÙĨÛĮ

-0.15

tright

-0.14

(strtolower

-0.14

wyn

-0.14

sWith

-0.14

 ÑĢÐ°ÑģÐº

-0.13

ula

-0.13

POSITIVE LOGITS

ìĿĮ

0.15

ace

0.15

ibling

0.14

 Silva

0.14

imoto

0.14

Ace

0.14

 odds

0.14

.sdk

0.14

ç´¢

0.14

oden

0.14

Activations Density 0.009%

phrases that indicate increasing amounts or degrees of something

No Comments

No Known Activations