INDEX

Explanations

instances of the word "own" in various contexts related to personal ownership or individuality

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

 itself

-0.23

 Himself

-0.17

 themselves

-0.16

alu

-0.15

alian

-0.15

 ÑģÐ°Ð¼Ð°

-0.15

 both

-0.15

ppe

-0.14

atte

-0.14

eless

-0.14

POSITIVE LOGITS

 personal

0.26

 version

0.26

 accord

0.24

-brand

0.24

 unique

0.24

personal

0.21

 particular

0.21

/internal

0.20

 UNIQUE

0.20

Unique

0.20

Activations Density 0.055%

instances of the word "own" in various contexts related to personal ownership or individuality

No Comments

No Known Activations