© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 27-RESID-POST-AA
    11. 57087
    Prev
    Next
    INDEX
    Explanations

    meg

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Water
    -0.07
     Tibetan
    -0.06
     soils
    -0.06
     drawer
    -0.06
    ırı
    -0.06
    .Views
    -0.06
    (Abstract
    -0.06
    来了
    -0.06
     ("/
    -0.06
    dess
    -0.06
    POSITIVE LOGITS
    ования
    0.07
    modifiable
    0.07
     complained
    0.06
    aseña
    0.06
     انگ
    0.06
     คน
    0.06
     aumento
    0.06
     customization
    0.06
    ٔ
    0.06
    structor
    0.06
    Activations Density 0.002%

    No Known Activations