INDEX

Explanations

technical or scientific jargon related to experimental results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ãĥ¬ãĥ¼

-0.14

Î¸Î·

-0.14

unny

-0.14

à¤łà¤¨

-0.14

celik

-0.14

 errorCallback

-0.13

iece

-0.13

emap

-0.13

.EVT

-0.13

á»§

-0.13

POSITIVE LOGITS

 spin

0.35

 relaxation

0.32

 nuclear

0.32

 Nuclear

0.31

 Spin

0.30

 proton

0.30

spin

0.30

 spins

0.29

Spin

0.28

 spinning

0.28

Activations Density 0.007%

technical or scientific jargon related to experimental results

No Comments

No Known Activations