INDEX

Explanations

statements asserting the existence or truth of a subject or concept

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 fraught

-0.15

ÄħÅ¼

-0.14

sui

-0.14

tte

-0.14

ague

-0.14

ãģĵãģ¡ãĤī

-0.13

lier

-0.13

ãģĿãģĵ

-0.13

LEGRO

-0.13

etwork

-0.13

POSITIVE LOGITS

why

0.39

why

0.30

 true

0.29

WHY

0.25

true

0.24

ä¸ºä»Ģä¹Ī

0.23

 pourquoi

0.23

Why

0.23

Why

0.23

 True

0.21

Activations Density 0.130%

statements asserting the existence or truth of a subject or concept

No Comments

No Known Activations