INDEX

Explanations

references to national identities and notable figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

arsi

-0.16

rfl

-0.15

ito

-0.15

#ad

-0.15

Ø

-0.15

 Giá»Ľi

-0.14

vet

-0.14

AD

-0.14

Gate

-0.14

attend

-0.14

POSITIVE LOGITS

 arts

0.23

lid

0.23

 leider

0.21

 historic

0.20

 advise

0.20

 advoc

0.19

 assist

0.19

 dirig

0.18

lid

0.18

 autoc

0.17

Activations Density 0.029%

references to national identities and notable figures

No Comments

No Known Activations