INDEX

Explanations

instances of numerical data or statistics in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ardu

-0.16

anoi

-0.15

ivant

-0.15

 Kara

-0.15

anche

-0.15

icari

-0.14

ÑīÐ¸

-0.14

vang

-0.14

ano

-0.14

dit

-0.14

POSITIVE LOGITS

nam

0.19

Nam

0.16

eger

0.15

 Gard

0.14

 hesab

0.14

Nam

0.14

 Specifically

0.14

ippi

0.14

 namely

0.14

eg

0.13

Activations Density 0.315%

instances of numerical data or statistics in the text

No Comments

No Known Activations