INDEX

Explanations

criticisms of political figures and their actions regarding war and foreign policy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

artz

-0.16

 communist

-0.15

rink

-0.14

burst

-0.14

Ada

-0.14

laus

-0.14

 Babe

-0.14

 underground

-0.13

Aub

-0.13

POSITIVE LOGITS

 intervention

0.26

 Empire

0.26

 warm

0.25

 empire

0.25

 imperial

0.24

 Intervention

0.24

 imperialism

0.23

 interventions

0.23

 Imperial

0.23

neo

0.23

Activations Density 0.103%

criticisms of political figures and their actions regarding war and foreign policy

No Comments

No Known Activations