INDEX

Explanations

instances of the word "Brave" and terms associated with positive attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

.scalablytyped

-0.18

/xhtml

-0.17

istrovstvÃŃ

-0.16

nal

-0.16

uale

-0.15

sj

-0.15

Ø¹Ø¨

-0.15

iah

-0.15

-ÑĤÐ¾

-0.15

inker

-0.14

POSITIVE LOGITS

ness

0.48

NESS

0.37

ly

0.33

mente

0.28

ities

0.28

 enough

0.23

 ness

0.23

ity

0.23

-looking

0.23

nes

0.22

Activations Density 0.265%

instances of the word "Brave" and terms associated with positive attributes

No Comments

No Known Activations