INDEX

Explanations

technical specifications and features of products, particularly in software and technology contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dera

-0.14

-0.13

inke

-0.13

à¸§à¸£à¸£

-0.13

imat

-0.13

modx

-0.13

uja

-0.13

imos

-0.13

ockey

-0.13

íĤ¹

-0.13

POSITIVE LOGITS

features

0.20

 features

0.19

 FEATURES

0.16

 feat

0.15

Scrollbar

0.15

esser

0.15

/features

0.15

 Features

0.15

è±Ĭ

0.15

lob

0.14

Activations Density 0.150%

technical specifications and features of products, particularly in software and technology contexts

No Comments

No Known Activations