INDEX

Explanations

phrases related to conclusions or endings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Gry

-0.17

chai

-0.15

å¿ĺ

-0.14

nio

-0.13

 freshly

-0.13

esi

-0.13

 spirituality

-0.13

 Ø¨Ø§ÛĮ

-0.13

lez

-0.13

 Bryce

-0.13

POSITIVE LOGITS

/start

0.18

ovit

0.17

lassen

0.16

ows

0.16

olem

0.16

ilogue

0.15

dump

0.15

 Cres

0.15

à¸¥à¸ĩ

0.15

ilet

0.14

Activations Density 0.124%

phrases related to conclusions or endings

No Comments

No Known Activations