INDEX

Explanations

instances of the word "Smart" in various contexts related to technology or innovation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

verage

-0.15

attery

-0.15

hower

-0.15

ataire

-0.15

ammers

-0.15

hop

-0.15

atre

-0.15

ogne

-0.15

aison

-0.15

usk

-0.14

POSITIVE LOGITS

yp

0.23

est

0.20

ies

0.20

ened

0.19

phones

0.19

lek

0.18

ale

0.17

 Alec

0.17

phone

0.17

nes

0.16

Activations Density 0.023%

instances of the word "Smart" in various contexts related to technology or innovation

No Comments

No Known Activations