INDEX

Explanations

terms related to electronic technology and platforms

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

lect

-0.18

quam

-0.17

xD

-0.15

culos

-0.15

ungs

-0.14

uchs

-0.14

lei

-0.14

aday

-0.14

Ùĩ

-0.14

lex

-0.14

POSITIVE LOGITS

0.15

ystem

0.15

 Zhou

0.14

.appendTo

0.14

iers

0.14

_closure

0.13

DidEnter

0.13

ected

0.13

BarButtonItem

0.13

Activations Density 0.009%

terms related to electronic technology and platforms

No Comments

No Known Activations