INDEX

Explanations

references to government and its functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Government

-0.20

 government

-0.19

 Governments

-0.18

 Governance

-0.18

 governments

-0.18

government

-0.18

æĶ¿åºľ

-0.17

 governo

-0.17

Government

-0.17

ros

-0.16

POSITIVE LOGITS

ality

0.32

ally

0.31

al

0.24

 agencies

0.24

 bodies

0.22

-owned

0.22

wide

0.21

-run

0.21

 officials

0.20

 shutdown

0.19

Activations Density 0.060%

references to government and its functions

No Comments

No Known Activations