INDEX

Explanations

references to the color white or its variations in context

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

Negative Logits

adesh

-0.16

agger

-0.15

 ÑĥÐ²

-0.15

amma

-0.15

 purple

-0.14

yny

-0.14

mann

-0.14

uby

-0.14

IMP

-0.14

emap

-0.14

POSITIVE LOGITS

WHITE

0.26

-white

0.25

 white

0.25

 WHITE

0.24

White

0.24

 White

0.23

white

0.22

 çĻ½

0.21

.White

0.20

 Ø³ÙģÛĮØ¯

0.20

Activations Density 0.072%

references to the color white or its variations in context

No Known Activations