INDEX

Explanations

word forms related to authority and governance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 ******************************************************************************↵

-0.17

oubles

-0.15

Dou

-0.15

ubes

-0.15

atoon

-0.15

 Dame

-0.15

ocular

-0.15

fram

-0.14

outer

-0.14

iquid

-0.14

POSITIVE LOGITS

zent

0.17

sÃŃ

0.16

 åī

0.15

trap

0.15

kid

0.15

kop

0.15

ekce

0.15

addtogroup

0.15

 gratuites

0.14

utut

0.14

Activations Density 0.124%

word forms related to authority and governance

No Comments

No Known Activations