INDEX

Explanations

technical terms and methods related to numerical analysis and mathematical modeling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 comb

-0.15

Ø¬Ø±

-0.14

 foreground

-0.14

foreground

-0.14

modity

-0.14

dup

-0.14

 Union

-0.13

 solidity

-0.13

requete

-0.13

Ð±Ð¸Ð½

-0.13

POSITIVE LOGITS

 integration

0.27

 Integration

0.27

Integration

0.27

ode

0.25

ODE

0.25

ode

0.24

 integrating

0.24

integration

0.23

Run

0.22

 integr

0.22

Activations Density 0.043%

technical terms and methods related to numerical analysis and mathematical modeling

No Comments

No Known Activations