INDEX

Explanations

references to open-source licensing and nonprofit organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

urm

-0.19

ydk

-0.16

æĿī

-0.14

Las

-0.14

(::

-0.14

uber

-0.13

yt

-0.13

 Ø³Ø±Ùħ

-0.13

 Twitter

-0.13

(Cl

-0.13

POSITIVE LOGITS

.gnu

0.23

 Affero

0.19

.tex

0.18

emacs

0.18

GNU

0.18

 shar

0.17

Č↵

0.17

GN

0.17

RCS

0.17

 Lisp

0.16

Activations Density 0.035%

references to open-source licensing and nonprofit organizations

No Comments

No Known Activations