INDEX

Explanations

terms related to facial deformities and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ÑħÐ¾Ð²

-0.14

 unconscious

-0.14

.tcp

-0.14

ayacak

-0.14

Recovered

-0.13

ä¹

-0.13

zej

-0.13

à¸Ľà¸£à¸°

-0.13

uru

-0.13

JNI

-0.13

POSITIVE LOGITS

 malformed

0.23

 anomalies

0.22

 defects

0.22

 congen

0.21

club

0.21

 club

0.21

 anomaly

0.20

 defect

0.20

 imper

0.20

 birth

0.20

Activations Density 0.019%

terms related to facial deformities and medical conditions

No Comments

No Known Activations