INDEX

Explanations

terms and concepts related to machine learning and deep learning architectures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ever

-0.16

oren

-0.16

éļĨ

-0.15

ĭ

-0.15

 undert

-0.14

è©±

-0.14

pson

-0.14

sett

-0.14

Å¡i

-0.14

 Ø¢Ø²Ø§Ø¯

-0.14

POSITIVE LOGITS

 functools

0.15

Ð¼ÐµÑĪ

0.15

inois

0.15

onom

0.14

.plugins

0.14

([]

0.14

UIF

0.14

ewe

0.14

éĢł

0.14

illow

0.14

Activations Density 0.047%

terms and concepts related to machine learning and deep learning architectures

No Comments

No Known Activations