© 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. 15-RESID-POST-AA
    11. 44704
    Prev
    Next
    INDEX
    Explanations

    cause and effect

    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
    Ur
    -0.06
    _department
    -0.06
    면적
    -0.06
    }';↵
    -0.06
    _ak
    -0.06
    _through
    -0.06
    들이
    -0.06
    interfaces
    -0.06
    แหน
    -0.06
    اهای
    -0.06
    POSITIVE LOGITS
     Limited
    0.06
    LEEP
    0.06
     reality
    0.06
    uição
    0.06
     geliş
    0.06
    *a
    0.06
     cellphone
    0.06
     namoro
    0.06
    Instr
    0.06
     coffee
    0.06
    Activations Density 0.009%

    No Known Activations