INDEX

Explanations

scientific measurements and their expressions in various units

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

enco

-0.16

oen

-0.15

cka

-0.14

lok

-0.14

 Laws

-0.14

æ²

-0.14

insky

-0.13

 premise

-0.13

azon

-0.13

law

-0.13

POSITIVE LOGITS

iless

0.18

anship

0.17

0.15

omnia

0.15

arih

0.15

à¹Ħà¸§

0.14

à¤Ĥà¤ľ

0.14

aras

0.14

é³´

0.14

Activations Density 0.481%

scientific measurements and their expressions in various units

No Comments

No Known Activations