INDEX

Explanations

references to book series and sequels

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Heal

-0.16

ngr

-0.14

 Kund

-0.14

 Manson

-0.14

 proactive

-0.13

 Marilyn

-0.13

_foreign

-0.13

 coincidence

-0.13

 area

-0.13

ella

-0.13

POSITIVE LOGITS

 series

0.18

series

0.17

-series

0.17

istrovstvÃŃ

0.16

akest

0.16

eniz

0.15

/Foundation

0.14

 PROCUREMENT

0.14

iado

0.14

ÑĸÑı

0.14

Activations Density 0.097%

references to book series and sequels

No Known Activations