INDEX

Explanations

words and phrases related to passwords and security measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Ð²Ð¸ÑĩÐ°Ð¹

-0.17

etro

-0.17

upy

-0.16

sey

-0.15

ÏģÎºÎµ

-0.15

avez

-0.15

inois

-0.15

dac

-0.14

iesta

-0.14

athers

-0.14

POSITIVE LOGITS

ned

0.17

castle

0.15

 Mitar

0.14

elmet

0.14

folios

0.14

Î¹Ïĩ

0.14

.getApp

0.13

radan

0.13

Ð°Ð½Ñĭ

0.13

arel

0.13

Activations Density 0.012%

words and phrases related to passwords and security measures

No Comments

No Known Activations