INDEX

Explanations

references to Ubuntu software and its features or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kova

-0.17

peria

-0.16

_LOADED

-0.15

 Vanderbilt

-0.15

kul

-0.15

 Sinai

-0.15

mek

-0.14

oku

-0.14

ocities

-0.14

 Nissan

-0.14

POSITIVE LOGITS

/ubuntu

0.30

ubuntu

0.22

LTS

0.20

Ubuntu

0.19

 Ubuntu

0.19

.deb

0.18

 Maver

0.18

 Canonical

0.18

 ubuntu

0.17

Canonical

0.17

Activations Density 0.009%

references to Ubuntu software and its features or issues

No Comments

No Known Activations