INDEX

Explanations

references to numerical analysis related to human characteristics and their symbolic representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Ð¿Ð¾Ð±Ð°

-0.20

ebb

-0.15

ukan

-0.15

inness

-0.14

acea

-0.14

æĢİä¹Ī

-0.13

fu

-0.13

 callable

-0.13

fell

-0.13

uli

-0.13

POSITIVE LOGITS

urga

0.16

 revealed

0.15

 morph

0.15

 substant

0.15

ivent

0.15

asaki

0.14

abal

0.14

 originals

0.14

ondo

0.14

 researching

0.14

Activations Density 0.092%

references to numerical analysis related to human characteristics and their symbolic representations

No Comments

No Known Activations