INDEX

Explanations

references to grids or grid-like structures in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ynet

-0.15

ynes

-0.15

urses

-0.14

IZE

-0.14

 McGu

-0.14

udy

-0.14

ekil

-0.13

oplast

-0.13

pis

-0.13

andes

-0.13

POSITIVE LOGITS

work

0.18

ahlen

0.15

angl

0.15

/system

0.14

anic

0.14

 BehaviorSubject

0.14

ieran

0.13

Ø§Ù¾

0.13

otic

0.13

Activations Density 0.005%

references to grids or grid-like structures in various contexts

No Comments

No Known Activations