INDEX

Explanations

instances of the word "change" and variations of it in relation to identity or roles

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

©

-0.14

ingroup

-0.14

achuset

-0.14

emodel

-0.14

OfType

-0.13

heten

-0.13

 corrections

-0.13

ORITY

-0.13

adoo

-0.13

OGRAPH

-0.13

POSITIVE LOGITS

 gears

0.31

 tack

0.29

 direction

0.28

 sides

0.26

 focus

0.26

 lanes

0.23

 allegiance

0.23

æĸ¹åĲĳ

0.23

 course

0.23

 sexes

0.23

Activations Density 0.085%

instances of the word "change" and variations of it in relation to identity or roles

No Comments

No Known Activations