INDEX

Explanations

references to academic research and publications in artificial intelligence

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

umbo

-0.18

icators

-0.15

pri

-0.15

 Tune

-0.14

 math

-0.14

gregator

-0.14

 agon

-0.14

akit

-0.13

POSITIVE LOGITS

 image

0.25

 anomaly

0.23

 machine

0.23

 Machine

0.23

 sentiment

0.22

Machine

0.22

omaly

0.22

 Image

0.21

image

0.20

 classification

0.20

Activations Density 0.143%

references to academic research and publications in artificial intelligence

No Comments

No Known Activations