INDEX

Explanations

elements related to property and ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

acente

-0.18

adora

-0.18

atorio

-0.17

idente

-0.16

ienda

-0.16

icao

-0.16

eldo

-0.16

zzle

-0.16

aciente

-0.15

acija

-0.15

POSITIVE LOGITS

icos

0.23

nicos

0.23

tones

0.23

adores

0.22

licos

0.22

udos

0.21

ativos

0.21

uros

0.20

hores

0.20

osos

0.20

Activations Density 0.060%

elements related to property and ownership

No Comments

No Known Activations