© 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 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. 19-RESID-POST-AA
    11. 126432
    Prev
    Next
    INDEX
    Explanations

    deployed models

    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
    łem
    -0.07
    KW
    -0.07
     DefaultValue
    -0.06
     име
    -0.06
    iframe
    -0.06
    awning
    -0.06
    dance
    -0.06
    /op
    -0.06
     людина
    -0.06
    nano
    -0.06
    POSITIVE LOGITS
     seni
    0.07
    _Module
    0.07
     Uint
    0.07
     Prest
    0.06
     ↓
    0.06
    .less
    0.06
     antig
    0.06
     Selling
    0.06
     eighteen
    0.06
    .getID
    0.06
    Activations Density 0.034%

    No Known Activations