INDEX

Explanations

punctuation marks that indicate the flow or structure of text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Whilst

-0.21

 whilst

-0.19

Whilst

-0.14

Many

-0.13

igin

-0.13

asic

-0.13

indow

-0.12

atron

-0.12

ÙĬÙĥÙĬ

-0.12

 Tarif

-0.12

POSITIVE LOGITS

Or

0.26

 Hell

0.25

Um

0.24

Um

0.24

 Seriously

0.23

Seriously

0.23

 honestly

0.23

Or

0.23

 honest

0.22

Hell

0.21

Activations Density 0.241%

punctuation marks that indicate the flow or structure of text

No Comments

No Known Activations