INDEX

Explanations

nouns and action words related to registration and record keeping

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

íĥľ

-0.16

 Pitt

-0.15

 Singh

-0.15

 Hilton

-0.15

sp

-0.15

rig

-0.14

 Henrik

-0.14

ut

-0.14

UGIN

-0.14

STRUCT

-0.14

POSITIVE LOGITS

esiz

0.19

deaux

0.17

apolis

0.15

-uri

0.15

_lazy

0.15

Ð²ÐµÐ½

0.15

.EXIT

0.15

odie

0.14

odnÃŃ

0.14

 <!--[

0.14

Activations Density 0.038%

nouns and action words related to registration and record keeping

No Known Activations