INDEX

Explanations

activities and performances related to historical reenactments

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

éĻµ

-0.17

 operative

-0.15

 Borders

-0.15

 stri

-0.14

WebResponse

-0.14

jak

-0.14

kea

-0.14

Borders

-0.14

 Glas

-0.14

Ì£

-0.14

POSITIVE LOGITS

 Spanish

0.25

Spanish

0.23

 colonial

0.23

 Spain

0.23

 Span

0.20

 missions

0.20

 Colonial

0.20

 Europeans

0.19

 Indies

0.19

Jes

0.19

Activations Density 0.056%

activities and performances related to historical reenactments

No Comments

No Known Activations