INDEX

Explanations

phrases that indicate actions taken to leave or share information online

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 Ð´ÑĥÑĪ

-0.15

ãģ®ãģł

-0.14

 Gast

-0.14

oucher

-0.14

Ð¶Ð´

-0.14

esz

-0.14

 Frontier

-0.14

 Dummy

-0.14

reducers

-0.14

#/

-0.14

POSITIVE LOGITS

ontology

0.17

rawer

0.16

 Ð½Ð¸Ð¶Ðµ

0.16

.Generated

0.15

/***/

0.15

Ð¡Ðł

0.15

à¹īà¸²à¸«

0.14

/******/

0.14

anner

0.14

Äĩe

0.14

Activations Density 0.253%

phrases that indicate actions taken to leave or share information online

No Comments

No Known Activations