INDEX

Explanations

instances of lying down or being in a prone position

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

éĤª

-0.15

 standing

-0.15

 Standing

-0.15

 cages

-0.15

stands

-0.15

 cáº§m

-0.15

å³

-0.14

 vlas

-0.14

Dip

-0.14

bob

-0.14

POSITIVE LOGITS

 lying

0.29

lie

0.28

 spraw

0.26

lay

0.25

Lie

0.23

 lies

0.22

 prone

0.22

 flat

0.22

 floor

0.22

Lay

0.21

Activations Density 0.104%

instances of lying down or being in a prone position

No Comments

No Known Activations