INDEX

Explanations

mathematical concepts and definitions, particularly those involving operators and functions in spectral theory

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 Pitch

-0.16

ekli

-0.16

 slack

-0.16

askell

-0.15

 Babylon

-0.15

-0.14

 digest

-0.14

 Buster

-0.14

æĺ

-0.14

Oro

-0.14

POSITIVE LOGITS

 operator

0.47

 operators

0.42

 Operator

0.39

 Operators

0.38

Operator

0.38

operator

0.38

-operator

0.35

Operators

0.35

operators

0.35

.operator

0.34

Activations Density 0.072%

mathematical concepts and definitions, particularly those involving operators and functions in spectral theory

No Comments

No Known Activations