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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 90804
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     놓
    -0.09
    (Location
    -0.06
     searchBar
    -0.06
     QMainWindow
    -0.06
    /mainwindow
    -0.06
     MERCHANTABILITY
    -0.06
     addObject
    -0.06
     wParam
    -0.06
     assay
    -0.06
     configurations
    -0.06
    POSITIVE LOGITS
    ِين
    0.07
    neg
    0.07
    덕
    0.06
    _csv
    0.06
    -IS
    0.06
     (?
    0.06
    ?↵↵↵
    0.06
     Heights
    0.06
    (suffix
    0.06
    cherche
    0.06
    Activations Density 0.076%

    No Known Activations