© 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. 27299
    Prev
    Next
    INDEX
    Explanations

    personal stories

    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
    _handle
    -0.07
     stu
    -0.07
    little
    -0.06
     ly
    -0.06
    standing
    -0.06
     thirst
    -0.06
    .$.
    -0.06
     whats
    -0.06
    ्रमण
    -0.06
     foremost
    -0.06
    POSITIVE LOGITS
    ственное
    0.07
    riteln
    0.06
     uživatel
    0.06
     μπορεί
    0.06
    例
    0.06
     obviously
    0.06
    ограм
    0.06
    aintenance
    0.06
    ось
    0.06
     ignore
    0.06
    Activations Density 0.005%

    No Known Activations