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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19-RESID-POST-AA
    11. 109725
    Prev
    Next
    INDEX
    Explanations

    suite

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    анием
    -0.06
    (['
    -0.06
     word
    -0.06
    Pedido
    -0.06
    Global
    -0.06
     vacation
    -0.06
     beh
    -0.06
    能够
    -0.06
    Diamond
    -0.06
    位
    -0.06
    POSITIVE LOGITS
     ister
    0.07
    购买
    0.07
    styleType
    0.07
    ORIZONTAL
    0.07
     허
    0.06
    omez
    0.06
     silky
    0.06
     повинні
    0.06
     сколько
    0.06
    	dataType
    0.06
    Activations Density 0.006%

    No Known Activations