Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 20363
    Prev
    Next
    INDEX
    Explanations

    of

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Password
    -0.06
     kaydet
    -0.06
    nen
    -0.06
    /tool
    -0.06
    ()↵↵↵↵
    -0.06
     Casinos
    -0.06
     authToken
    -0.06
    emen
    -0.06
    .Roles
    -0.06
    League
    -0.06
    POSITIVE LOGITS
     кол
    0.07
     tra
    0.07
    852
    0.06
     append
    0.06
     nonexistent
    0.06
     xt
    0.06
     ay
    0.06
    ้อง
    0.06
     JAXB
    0.06
    パン
    0.06
    Activations Density 0.003%

    No Known Activations