INDEX

Explanations

references to political figures and their titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Peaks

-0.16

 Copp

-0.15

ÏĥÎº

-0.15

izoph

-0.14

Ð°ÑĤÐ°ÑĢ

-0.14

opol

-0.14

lius

-0.14

Ã¥de

-0.14

istles

-0.14

arehouse

-0.14

POSITIVE LOGITS

 White

0.31

 Oval

0.29

White

0.26

 President

0.22

 presidential

0.22

 WHITE

0.22

 Presidential

0.20

 Secret

0.20

 Residence

0.19

 president

0.19

Activations Density 0.104%

references to political figures and their titles

No Comments

No Known Activations