INDEX

Explanations

references to government officials 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

 Forums

-0.17

ãĥ³ãĤ°

-0.16

 Presidents

-0.16

 presidents

-0.16

 Parliament

-0.16

à¸§à¸¢

-0.16

ClientRect

-0.16

riÃ¨re

-0.15

Obsolete

-0.15

 Stub

-0.15

POSITIVE LOGITS

Nom

0.27

 nominee

0.26

 secretary

0.25

 Secretary

0.25

Nom

0.24

nom

0.23

nom

0.23

 nomination

0.22

 nominate

0.21

Secretary

0.20

Activations Density 0.109%

references to government officials and their titles

No Comments

No Known Activations