INDEX

Explanations

details related to clothing and accessories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 shirts

-0.18

 uniforms

-0.17

ÑĥÐ³

-0.16

áº¡i

-0.15

 velvet

-0.15

 dresses

-0.15

 Shirt

-0.15

 prive

-0.14

igar

-0.14

 garment

-0.14

POSITIVE LOGITS

 matching

0.23

 accessories

0.21

Matching

0.20

 accessory

0.19

matching

0.19

 accessor

0.18

 Matching

0.18

Accessor

0.17

 Accessories

0.16

 complementary

0.15

Activations Density 0.098%

details related to clothing and accessories

No Comments

No Known Activations