INDEX

Explanations

terms related to re-entry and second chances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

.elementAt

-0.17

edn

-0.15

ICAST

-0.15

 ÙĪØ§ÙĤØ¹

-0.15

mmas

-0.15

 znam

-0.14

åı·

-0.14

Ð»Ð¸Ð½Ð¸

-0.14

adh

-0.13

omor

-0.13

POSITIVE LOGITS

 metab

0.19

met

0.19

met

0.19

ros

0.18

 Wilson

0.17

Met

0.17

 Ð¼ÐµÑĤ

0.17

 mÃ©t

0.17

 Metropolitan

0.16

 metam

0.16

Activations Density 0.034%

terms related to re-entry and second chances

No Comments

No Known Activations