INDEX

Explanations

concepts and terminology related to mathematical or logical frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

atak

-0.18

izik

-0.15

 Sink

-0.15

hma

-0.14

 sink

-0.14

mr

-0.14

 laps

-0.14

producer

-0.14

_TestCase

-0.14

mur

-0.13

POSITIVE LOGITS

 additional

0.23

 added

0.22

added

0.20

additional

0.20

 thÃªm

0.18

 Added

0.18

 addition

0.17

-added

0.17

anut

0.16

itor

0.16

Activations Density 0.248%

concepts and terminology related to mathematical or logical frameworks

No Comments

No Known Activations