INDEX

Explanations

phrases related to purposes or intentions behind actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

UnderTest

-0.15

redo

-0.14

robe

-0.14

Ð½Ð¾Ðº

-0.13

vos

-0.13

odie

-0.13

à¹ĥà¸Ī

-0.12

\Mapping

-0.12

EGA

-0.12

illes

-0.12

POSITIVE LOGITS

 purposes

1.22

 purpose

0.99

purpose

0.81

 Purpose

0.79

 PURPOSE

0.78

Purpose

0.77

-purpose

0.66

 sake

0.60

çĽ®çļĦ

0.59

urpose

0.59

Activations Density 0.166%

phrases related to purposes or intentions behind actions

No Comments

No Known Activations