INDEX

Explanations

references to political parties and their leaders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

anki

-0.17

pane

-0.15

ende

-0.14

odb

-0.14

 Liberties

-0.14

stit

-0.14

enti

-0.13

 Sentinel

-0.13

.apple

-0.13

aight

-0.13

POSITIVE LOGITS

 Party

0.33

 party

0.32

Party

0.29

 PARTY

0.28

 leader

0.26

_party

0.26

.party

0.23

party

0.23

-party

0.22

 Leader

0.20

Activations Density 0.042%

references to political parties and their leaders

No Comments

No Known Activations