INDEX

Explanations

references to historical artifacts and their repatriation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

okers

-0.17

.structure

-0.15

olla

-0.15

-collapse

-0.14

awah

-0.14

å¤ªéĥİ

-0.13

ProcessEvent

-0.13

 addCriterion

-0.13

 tail

-0.13

 Tail

-0.13

POSITIVE LOGITS

 museums

0.28

 museum

0.27

 Museum

0.25

 stolen

0.23

useum

0.22

 returns

0.22

 Ð¼ÑĥÐ·

0.21

 Muse

0.21

 theft

0.21

 Returns

0.20

Activations Density 0.046%

references to historical artifacts and their repatriation

No Comments

No Known Activations