© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-RESID-POST-AA
    11. 2405
    Prev
    Next
    INDEX
    Explanations

    incentive

    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
    lder
    -0.06
     organs
    -0.06
    颜
    -0.06
     dou
    -0.06
    垂
    -0.06
     Ко
    -0.06
     faults
    -0.06
     Раз
    -0.06
    ��
    -0.06
     Recon
    -0.06
    POSITIVE LOGITS
     incentives
    0.11
     incentive
    0.10
    (eventName
    0.07
    Gesture
    0.06
    acciones
    0.06
     penalty
    0.06
     hızlı
    0.06
     Açık
    0.06
     çeşit
    0.06
     backed
    0.06
    Activations Density 0.004%

    No Known Activations