© 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. 32519
    Prev
    Next
    INDEX
    Explanations

    Random text snippets

    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
     Kiểm
    -0.08
    Commerce
    -0.07
     Setting
    -0.07
    مح
    -0.07
    entionPolicy
    -0.07
    ';';
    -0.06
     चलत
    -0.06
     Fakültesi
    -0.06
    VERIFY
    -0.06
    viewModel
    -0.06
    POSITIVE LOGITS
    datasets
    0.06
    Pick
    0.06
    431
    0.06
     Carlos
    0.06
     dors
    0.06
     grosse
    0.06
     collections
    0.06
     try
    0.06
    _peer
    0.06
     explosions
    0.06
    Activations Density 0.005%

    No Known Activations