INDEX

Explanations

references to definitions and citations within a mathematical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

[](

-0.15

æĬľ

-0.14

åĿĬ

-0.14

acht

-0.14

stat

-0.14

á»ķ

-0.14

cker

-0.14

Ð¾Ð²Ð¾ÑĢ

-0.13

ermen

-0.13

luk

-0.13

POSITIVE LOGITS

 Section

0.22

Sec

0.22

Sub

0.21

Cor

0.20

 Remark

0.20

 section

0.19

 Paper

0.19

 Append

0.19

eq

0.19

 Formula

0.18

Activations Density 0.208%

references to definitions and citations within a mathematical context

No Comments

No Known Activations