INDEX

Explanations

phrases indicating obligation or responsibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

odore

-0.16

allo

-0.14

ish

-0.14

ãĥ³ãĥĲãĥ¼

-0.14

Ð°Ð»Ð¾Ð³

-0.13

æĶ

-0.13

loff

-0.13

xt

-0.13

afka

-0.13

amu

-0.13

POSITIVE LOGITS

umed

0.16

eldo

0.15

ocommerce

0.15

plat

0.14

.***.***

0.14

agate

0.14

0.13

ussen

0.13

quelle

0.13

 trÃŃ

0.13

Activations Density 0.158%

phrases indicating obligation or responsibility

No Comments

No Known Activations