INDEX

Explanations

terms related to overall well-being and health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

idal

-0.15

\grid

-0.15

ÛĮØ§ÙĨ

-0.15

elson

-0.14

die

-0.14

sport

-0.14

à¥įà¤µà¤°

-0.14

otty

-0.14

werk

-0.13

elect

-0.13

POSITIVE LOGITS

AndPassword

0.16

Verdana

0.14

-health

0.14

ä¹ħ

0.14

 à¤īà¤ł

0.14

0.13

rong

0.13

ÑĸÑĪ

0.13

 health

0.13

Activations Density 0.046%

terms related to overall well-being and health

No Comments

No Known Activations