INDEX

Explanations

references to mathematical exercises and their solutions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

etting

-0.16

IMG

-0.15

 hood

-0.15

hood

-0.14

 decltype

-0.14

aida

-0.13

 national

-0.13

 Dissertation

-0.13

 cost

-0.13

upy

-0.13

POSITIVE LOGITS

 exercise

0.18

 challenge

0.18

 Challenge

0.18

Challenge

0.18

 exercises

0.17

challenge

0.17

 challenges

0.16

 ejercicio

0.16

ONUS

0.16

 Exercise

0.15

Activations Density 0.118%

references to mathematical exercises and their solutions

No Known Activations