INDEX

Explanations

references to individuality and personal ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 itself

-0.23

 Himself

-0.18

 themselves

-0.16

alian

-0.15

pper

-0.15

strup

-0.15

alu

-0.14

 himself

-0.14

stract

-0.14

inous

-0.14

POSITIVE LOGITS

 unique

0.27

 version

0.26

-brand

0.25

 accord

0.25

 personal

0.23

 particular

0.23

 distinctive

0.22

 UNIQUE

0.21

Unique

0.21

unique

0.21

Activations Density 0.054%

references to individuality and personal ownership

No Comments

No Known Activations