INDEX

Explanations

keywords related to relationships and community values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 ::::::::

-0.18

ï»¿#

-0.17

 massaggi

-0.16

-BEGIN

-0.15

icket

-0.15

ÃĮ

-0.14

@nate

-0.14

ÐºÐ¾Ð²Ð°

-0.14

/mainwindow

-0.14

frau

-0.14

POSITIVE LOGITS

(or

0.17

ä¹ĭä¸Ģ

0.13

ing

0.13

(s

0.13

ailability

0.13

 Renaissance

0.13

hips

0.13

—

0.13

 Geld

0.13

as

0.12

Activations Density 0.018%

keywords related to relationships and community values

No Comments

No Known Activations