INDEX

Explanations

references to historical and cultural sites or artifacts

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

éĻ

-0.15

ossier

-0.14

/umd

-0.14

ecret

-0.14

UIL

-0.14

ãĤ¤ãĥ³ãĥĪ

-0.14

Ä©a

-0.13

isclosed

-0.13

incare

-0.13

 Constructs

-0.13

POSITIVE LOGITS

 fres

0.28

 panels

0.24

 panel

0.21

 relief

0.21

 wall

0.20

 Panels

0.19

 Relief

0.19

 ceiling

0.19

 Narrative

0.18

 Fres

0.18

Activations Density 0.137%

references to historical and cultural sites or artifacts

No Comments

No Known Activations