INDEX

Explanations

terms related to intrusiveness or intrusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ÏĥÏĦÎµ

-0.16

istrat

-0.15

ores

-0.15

enez

-0.14

yat

-0.14

antha

-0.14

aed

-0.14

ikit

-0.14

ing

-0.14

ibility

-0.14

POSITIVE LOGITS

 intr

0.37

 Intr

0.36

intr

0.27

insics

0.25

acellular

0.20

UMENT

0.20

INTR

0.20

 intra

0.19

usion

0.19

avenous

0.19

Activations Density 0.013%

terms related to intrusiveness or intrusion

No Comments

No Known Activations