INDEX

Explanations

specific brand or product names related to technology and software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

polator

-0.18

cla

-0.15

Ø³Ø§ÙĦ

-0.15

jen

-0.15

à¸µà¹Ģà¸Ķ

-0.15

âĢĮÙħ

-0.15

ipel

-0.14

sage

-0.14

ãģ¡ãģ¯

-0.14

eteria

-0.14

POSITIVE LOGITS

aller

0.15

 none

0.14

èµ°

0.14

/loader

0.14

WebHost

0.14

 pace

0.14

 NONE

0.13

getattr

0.13

 careful

0.13

 importer

0.13

Activations Density 0.395%

specific brand or product names related to technology and software

No Comments

No Known Activations