© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 21788
    Prev
    Next
    INDEX
    Explanations

    drawing shapes

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ें,
    -0.07
    _context
    -0.07
    /TR
    -0.07
     ER
    -0.07
     sword
    -0.07
     Fra
    -0.07
     第二
    -0.06
    悉
    -0.06
     flavor
    -0.06
     competitions
    -0.06
    POSITIVE LOGITS
    ClassNotFoundException
    0.06
    Ellipse
    0.06
    usaha
    0.06
    Hum
    0.06
    @NgModule
    0.06
     thước
    0.06
     getView
    0.06
    _Class
    0.06
     Dorothy
    0.06
     сообщ
    0.06
    Activations Density 0.004%

    No Known Activations