© 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. 127518
    Prev
    Next
    INDEX
    Explanations

    code filenames

    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
     Anyway
    -0.07
    /test
    -0.07
     Hav
    -0.06
     Hol
    -0.06
    _unicode
    -0.06
    -star
    -0.06
     Dale
    -0.06
     LaTeX
    -0.06
    qed
    -0.06
    丈夫
    -0.06
    POSITIVE LOGITS
    (Op
    0.07
     visited
    0.07
    HY
    0.06
     Pf
    0.06
    <dyn
    0.06
     П
    0.06
    gorm
    0.06
    怕
    0.06
    ιβ
    0.06
    rength
    0.06
    Activations Density 0.014%

    No Known Activations