INDEX

Explanations

references to nationalities and ethnicities, particularly focusing on Asian cultures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ular

-0.16

adlo

-0.15

ley

-0.14

bersome

-0.14

division

-0.14

inged

-0.14

cean

-0.14

lix

-0.13

eson

-0.13

less

-0.13

POSITIVE LOGITS

-American

0.34

-Russian

0.26

-Americans

0.26

-speaking

0.22

-born

0.21

-flag

0.21

ischer

0.20

-made

0.19

istan

0.18

ische

0.17

Activations Density 0.253%

references to nationalities and ethnicities, particularly focusing on Asian cultures

No Comments

No Known Activations