INDEX

Explanations

terms related to vacancies or empty spaces

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

oteca

-0.18

ÑģÑĥÑĤ

-0.16

Rif

-0.15

onto

-0.15

egan

-0.15

oyal

-0.14

acon

-0.14

GI

-0.14

éĬ

-0.14

ahn

-0.14

POSITIVE LOGITS

uum

0.26

ancy

0.21

ancies

0.20

Vac

0.19

 cleaner

0.18

vvm

0.17

umm

0.17

vac

0.17

vac

0.17

arella

0.16

Activations Density 0.011%

terms related to vacancies or empty spaces

No Comments

No Known Activations