INDEX

Explanations

references to games and interactive activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 promin

-0.18

Abb

-0.16

 blow

-0.15

 DateTimeOffset

-0.14

 amat

-0.14

å§Ķåĳĺ

-0.14

 :-↵

-0.14

Tub

-0.14

Exc

-0.13

Ã¤

-0.13

POSITIVE LOGITS

Äĥ

0.26

 Romanian

0.23

 Romania

0.21

 Buch

0.21

ului

0.20

.ro

0.20

 Banc

0.19

ÈĻ

0.19

Å£

0.18

Äĥr

0.18

Activations Density 0.125%

references to games and interactive activities

No Comments

No Known Activations