© 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. 27-RESID-POST-AA
    11. 44924
    Prev
    Next
    INDEX
    Explanations

    building

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Proxy
    -0.06
     ump
    -0.06
     valida
    -0.06
     parti
    -0.06
     seam
    -0.06
     Whatsapp
    -0.06
     Чтобы
    -0.06
    Esta
    -0.06
     hope
    -0.05
    	points
    -0.05
    POSITIVE LOGITS
     buildings
    0.09
    ่น
    0.08
    ีร
    0.07
     paintings
    0.07
     building
    0.07
    (↵↵
    0.07
    шло
    0.07
    建筑
    0.07
    (fill
    0.07
     Buildings
    0.07
    Activations Density 0.016%

    No Known Activations