INDEX

Explanations

references to possession or ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

overy

-0.15

 Fairfield

-0.14

ingham

-0.14

 addCriterion

-0.14

 ones

-0.14

rawn

-0.14

IPPING

-0.14

ock

-0.14

ä¿Ĺ

-0.14

ifen

-0.13

POSITIVE LOGITS

ced

0.28

eldo

0.26

elo

0.26

erte

0.26

ces

0.25

 propia

0.25

cede

0.24

yo

0.24

jeta

0.24

friend

0.24

Activations Density 0.017%

references to possession or ownership

No Comments

No Known Activations