INDEX

Explanations

mathematical notations and symbols

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

licos

-0.15

bane

-0.14

ICON

-0.14

omo

-0.14

 Kaynak

-0.14

azo

-0.14

ennie

-0.14

ire

-0.14

.RightToLeft

-0.13

POSITIVE LOGITS

.cz

0.17

ìĤ

0.17

orama

0.17

au

0.15

 subject

0.15

iture

0.14

arella

0.14

 valid

0.14

valid

0.14

wald

0.14

Activations Density 0.107%

mathematical notations and symbols

No Comments

No Known Activations