INDEX

Explanations

terms related to property or ownership concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

er

-0.39

eras

-0.27

Ø±

-0.26

-0.25

erne

-0.24

ln

-0.23

ero

-0.23

lib

-0.22

erk

-0.21

eria

-0.21

POSITIVE LOGITS

licit

0.24

licity

0.23

lica

0.23

licate

0.22

lications

0.22

stakes

0.21

loid

0.20

loi

0.20

artment

0.19

lication

0.18

Activations Density 0.125%

terms related to property or ownership concepts

No Comments

No Known Activations