© 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. 23997
    Prev
    Next
    INDEX
    Explanations

    personal reflection

    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
    [val
    -0.08
     playoffs
    -0.07
    Main
    -0.07
    type
    -0.06
     Business
    -0.06
     truth
    -0.06
    隐藏
    -0.06
    .DialogInterface
    -0.06
     Arr
    -0.06
    [str
    -0.06
    POSITIVE LOGITS
    ��
    0.09
    蒂
    0.07
    μή
    0.07
    GU
    0.07
    ΑΠ
    0.07
    HI
    0.06
     зависим
    0.06
     собою
    0.06
     mutlu
    0.06
    タン
    0.06
    Activations Density 0.056%

    No Known Activations