INDEX

Explanations

references to political leaders and government activities

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

oko

-0.16

orex

-0.15

abbo

-0.15

erland

-0.14

erce

-0.14

ÄĽtÅ¡

-0.14

uft

-0.14

utzer

-0.14

Ð¾ÑĢÐ´Ð¸Ð½

-0.14

POSITIVE LOGITS

 Polit

0.26

 Party

0.24

Party

0.22

 polit

0.21

Polit

0.21

 party

0.20

 Political

0.19

ä¹¦è®°

0.17

 Standing

0.17

 PARTY

0.17

Activations Density 0.024%

references to political leaders and government activities

No Comments

No Known Activations