INDEX

Explanations

elements related to historical events and narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ãĤ®

-0.15

è

-0.15

aux

-0.15

/ay

-0.14

 claro

-0.14

cae

-0.14

ucha

-0.14

æī£

-0.14

 expos

-0.14

OGLE

-0.14

POSITIVE LOGITS

Ã¬

0.28

azione

0.25

Ã²

0.25

 possibile

0.24

zione

0.24

Ã¨

0.23

azioni

0.22

 giÃł

0.21

 giorn

0.21

Ã¹

0.21

Activations Density 0.453%

elements related to historical events and narratives

No Comments

No Known Activations