INDEX

Explanations

references to mathematical concepts and methods in data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

sat

-0.20

Bik

-0.16

 dress

-0.15

Ð¿Ð°

-0.15

 Dress

-0.15

rel

-0.15

Ð¾ÑıÐ½

-0.14

Sat

-0.14

 Bush

-0.14

 subnet

-0.14

POSITIVE LOGITS

.fft

0.28

fft

0.25

FFT

0.25

FFT

0.24

fft

0.24

 spectra

0.23

 taps

0.23

_fft

0.23

 Spect

0.23

 spectrum

0.22

Activations Density 0.091%

references to mathematical concepts and methods in data analysis

No Comments

No Known Activations