INDEX

Explanations

references to locations and property features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

vrd

-0.17

Ð¾Ð·Ð½Ð°

-0.14

Ð¾Ð¶Ð´

-0.14

atorium

-0.14

ÑıÐ³

-0.14

_userdata

-0.14

ibase

-0.14

à¸ªà¸³à¸Ļ

-0.14

 Kickstarter

-0.14

enta

-0.14

POSITIVE LOGITS

 golf

0.31

 Golf

0.27

 community

0.25

 guard

0.24

gol

0.24

 gated

0.24

HO

0.23

hoa

0.22

 amen

0.22

 master

0.22

Activations Density 0.065%

references to locations and property features

No Comments

No Known Activations