INDEX

Explanations

terms related to home decor and lighting fixtures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

utar

-0.15

pio

-0.14

UIT

-0.14

Folder

-0.14

 Ð´Ð¾Ñģ

-0.14

 heter

-0.14

Qin

-0.14

 Ramp

-0.13

illis

-0.13

 Roland

-0.13

POSITIVE LOGITS

 shade

0.28

 shades

0.27

 fixture

0.26

 Shade

0.24

 pendant

0.24

 Shades

0.24

 suspension

0.23

 hanging

0.23

 Flush

0.23

shade

0.23

Activations Density 0.021%

terms related to home decor and lighting fixtures

No Comments

No Known Activations