INDEX

Explanations

references to the Associated Press

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ple

-0.16

 hind

-0.16

à¸Ĺà¸£

-0.15

 pard

-0.15

 upper

-0.15

Weg

-0.15

 pastoral

-0.14

lingen

-0.14

abit

-0.14

à¤¹à¤¨

-0.14

POSITIVE LOGITS

oÄŁ

0.18

olet

0.17

askell

0.15

 JADX

0.15

å±Ĭ

0.15

éĮ

0.15

.dtd

0.15

ãĥĭãĥĥãĤ¯

0.15

ooter

0.14

edla

0.14

Activations Density 0.003%

references to the Associated Press

No Comments

No Known Activations