INDEX

Explanations

references to color or colors and their combinations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Color

-0.28

Colors

-0.27

_colors

-0.27

 colourful

-0.24

Colour

-0.24

 colours

-0.23

 Colour

-0.23

 Colors

-0.23

 colour

-0.23

_color

-0.23

POSITIVE LOGITS

-coded

0.32

 scheme

0.32

ation

0.30

 schemes

0.30

 Scheme

0.29

cheme

0.27

fully

0.27

blind

0.26

Scheme

0.25

chemes

0.25

Activations Density 0.050%

references to color or colors and their combinations in various contexts

No Comments

No Known Activations