INDEX

Explanations

phrases that introduce new content or features in a series or publication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

OMEM

-0.15

Åº

-0.14

imulator

-0.14

arg

-0.14

Īĺ

-0.14

_DLL

-0.13

olina

-0.13

lineno

-0.13

agrid

-0.13

 Å¼

-0.13

POSITIVE LOGITS

 profiles

0.30

 posts

0.29

 Profiles

0.28

 columns

0.24

 install

0.24

install

0.24

 series

0.24

Profiles

0.24

 feature

0.24

profiles

0.24

Activations Density 0.096%

phrases that introduce new content or features in a series or publication

No Comments

No Known Activations