INDEX

Explanations

mathematical notation and symbols, especially those related to equations and functions

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

ntl

-0.15

igel

-0.15

ellers

-0.15

asley

-0.15

OLT

-0.14

 fileprivate

-0.14

irie

-0.14

elters

-0.14

eler

-0.14

fos

-0.14

POSITIVE LOGITS

arrow

0.16

rightarrow

0.16

 Citizen

0.16

.symbol

0.16

oba

0.15

inspace

0.15

brace

0.15

.opend

0.15

one

0.15

ä¹ĭä¸Ģ

0.15

Activations Density 0.091%

mathematical notation and symbols, especially those related to equations and functions

No Comments

No Known Activations