INDEX

Explanations

a variety of programming and markup language syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

avigation

-0.27

elcome

-0.23

inux

-0.23

indows

-0.22

ICENSE

-0.22

etwork

-0.22

ubernetes

-0.21

atabase

-0.21

upport

-0.20

ernel

-0.20

POSITIVE LOGITS

enticate

0.23

olume

0.20

autiful

0.19

verity

0.19

\/\/

0.18

stride

0.18

ufact

0.18

ctrine

0.17

../../

0.17

asurement

0.17

Activations Density 0.120%

a variety of programming and markup language syntax

No Comments

No Known Activations