INDEX

Explanations

references to specific individuals or proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-0.32

auf

-0.29

iou

-0.27

iens

-0.26

ÛĮ

-0.26

aes

-0.25

aed

-0.24

aan

-0.24

aat

-0.24

POSITIVE LOGITS

dest

0.24

venture

0.23

vertisement

0.23

rian

0.23

ia

0.22

deo

0.21

ler

0.21

ewater

0.20

imir

0.20

ja

0.20

Activations Density 0.027%

references to specific individuals or proper nouns

No Comments

No Known Activations