INDEX

Explanations

proper nouns associated with leadership or prominent figures

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

 Wolver

-0.15

odox

-0.15

 Blackburn

-0.14

azon

-0.14

ÄįÃŃ

-0.14

acco

-0.14

izza

-0.14

uard

-0.14

iÃ³

-0.14

gress

-0.14

POSITIVE LOGITS

·

0.15

ĴĪ

0.14

zÄħd

0.14

 Familie

0.14

Ã¸d

0.14

 Andersen

0.14

ibilidade

0.13

 capacit

0.13

rawer

0.13

ulet

0.13

Activations Density 0.363%

proper nouns associated with leadership or prominent figures

No Comments

No Known Activations