© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 107752
    Prev
    Next
    INDEX
    Explanations

    Overview

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :block
    -0.06
    _cards
    -0.06
    _blocked
    -0.06
    locations
    -0.06
    	constructor
    -0.06
     sting
    -0.06
    Displayed
    -0.06
     signUp
    -0.06
     Lions
    -0.06
     cellul
    -0.06
    POSITIVE LOGITS
     πολύ
    0.07
    内
    0.07
     outnumber
    0.06
     overview
    0.06
     aid
    0.06
    更加
    0.06
     geliştir
    0.06
     chua
    0.06
    อว
    0.06
     equipped
    0.06
    Activations Density 0.002%

    No Known Activations