INDEX

Explanations

instances of the word "used" in various contexts

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

New Auto-Interp

Configuration

fnlp/Llama3_1-8B-Base-LXM-8x/Llama3_1-8B-Base-L22M-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_mlp_out

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

ulu

-0.16

 Functional

-0.15

oll

-0.15

 Ð±ÑĢÐ°

-0.15

venting

-0.15

uje

-0.14

 functional

-0.14

oje

-0.14

oth

-0.14

 Quart

-0.14

POSITIVE LOGITS

noÅĽÄĩ

0.17

usta

0.15

 sond

0.14

nev

0.14

ĮĴ

0.14

vsp

0.14

.opend

0.14

imdi

0.14

noÅĽci

0.13

 Williamson

0.13

Activations Density 0.018%

instances of the word "used" in various contexts

No Comments

No Known Activations