INDEX

Explanations

references to downloadable content and information related to products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Vis

-0.15

Inverse

-0.15

oid

-0.15

 inverse

-0.15

 somehow

-0.15

 counterfeit

-0.14

 locally

-0.14

 competitive

-0.14

 biological

-0.14

iece

-0.14

POSITIVE LOGITS

fee

0.17

elay

0.17

stants

0.17

_Syntax

0.15

ÏĥÏī

0.15

mmo

0.15

fee

0.15

ppv

0.15

alim

0.14

uled

0.14

Activations Density 0.218%

references to downloadable content and information related to products

No Comments

No Known Activations