INDEX

Explanations

terms related to automotive engineering and maintenance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 aspect

-0.15

Ð»Ð°ÑĤ

-0.14

WithData

-0.13

iaux

-0.13

 gridColumn

-0.13

æĸ¹éĿ¢

-0.13

 Opport

-0.13

imu

-0.12

’ÑĶ

-0.12

amo

-0.12

POSITIVE LOGITS

-specific

0.15

ONGL

0.15

acht

0.14

bject

0.14

/*/

0.13

íģ¼

0.13

idel

0.13

ØªÙī

0.13

affe

0.13

/../

0.13

Activations Density 0.551%

terms related to automotive engineering and maintenance

No Comments

No Known Activations