INDEX

Explanations

terms related to construction and architectural features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.15

 éĹ

-0.15

ÐµÐ»Ðµ

-0.14

ugins

-0.14

 Palo

-0.14

Trip

-0.14

ardown

-0.14

 Buddy

-0.14

imz

-0.13

 Trip

-0.13

POSITIVE LOGITS

 rains

0.31

 panels

0.27

cl

0.25

 panel

0.24

 Panels

0.24

 PANEL

0.23

facade

0.23

 curtain

0.21

 Panel

0.21

-panel

0.21

Activations Density 0.068%

terms related to construction and architectural features

No Comments

No Known Activations