INDEX

Explanations

references to communities and social dynamics, particularly focusing on cultural identities and interpersonal relationships

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

 aston

-0.16

ulumi

-0.16

apore

-0.15

umper

-0.14

ropoda

-0.14

aeda

-0.14

Shock

-0.14

ugh

-0.14

erras

-0.14

isoft

-0.14

POSITIVE LOGITS

 ready

0.28

 aware

0.23

 intent

0.23

 content

0.23

 unable

0.22

 moved

0.21

 cogn

0.21

 able

0.21

 feeling

0.21

fed

0.20

Activations Density 0.610%

references to communities and social dynamics, particularly focusing on cultural identities and interpersonal relationships

No Comments

No Known Activations