INDEX

Explanations

phrases and terms related to adherence to rules and regulations

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

eyn

-0.17

icina

-0.16

 éĩİ

-0.16

iale

-0.16

amed

-0.15

elier

-0.15

Wes

-0.14

 ÙħÛĮÙĦØ§Ø¯ÛĮ

-0.14

ature

-0.14

Away

-0.14

POSITIVE LOGITS

 strictly

0.25

scr

0.24

 fully

0.23

 string

0.22

/non

0.21

 Fully

0.19

Scr

0.18

fully

0.18

 strict

0.18

 Strict

0.17

Activations Density 0.026%

phrases and terms related to adherence to rules and regulations

No Comments

No Known Activations