INDEX

Explanations

terms related to mathematical modeling and numerical methods

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atif

-0.17

 Synd

-0.16

çīĻ

-0.15

iani

-0.15

 Winds

-0.14

èĵ

-0.14

eral

-0.13

 Fraser

-0.13

yles

-0.13

POSITIVE LOGITS

 equations

0.40

 equation

0.34

 differential

0.32

 governing

0.31

 integ

0.28

ifferential

0.26

 Differential

0.25

Nav

0.22

 partial

0.21

ODE

0.21

Activations Density 0.104%

terms related to mathematical modeling and numerical methods

No Comments

No Known Activations