INDEX

Explanations

statistics and numerical data related to education and student performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

otto

-0.17

avery

-0.17

itan

-0.16

alc

-0.15

 nÃło

-0.15

_firestore

-0.15

 Guest

-0.15

quo

-0.14

att

-0.14

 Measure

-0.14

POSITIVE LOGITS

wig

0.15

/GPL

0.15

AGMA

0.15

iki

0.15

istry

0.15

unma

0.14

iky

0.14

ertas

0.14

bum

0.14

thouse

0.14

Activations Density 0.093%

statistics and numerical data related to education and student performance

No Comments

No Known Activations