INDEX

Explanations

sections indicating navigation or location within a document

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

Ð¾Ð¿Ð¾Ð»

-0.17

uzzi

-0.16

ije

-0.14

illac

-0.14

ose

-0.14

amed

-0.14

ilk

-0.14

oton

-0.14

.hu

-0.14

abric

-0.14

POSITIVE LOGITS

 home

0.21

Home

0.20

 Home

0.20

HOME

0.17

 HOME

0.17

home

0.16

 homepage

0.16

aft

0.15

Ø¨ÙĪØ§Ø³Ø·Ø©

0.15

-home

0.15

Activations Density 0.003%

sections indicating navigation or location within a document

No Comments

No Known Activations