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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 104314
    Prev
    Next
    INDEX
    Explanations

    Empire

    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
     Cunningham
    -0.07
    OTION
    -0.07
     downloaded
    -0.06
    _produk
    -0.06
     recherche
    -0.06
    (training
    -0.06
     Veranst
    -0.06
     Toledo
    -0.06
    otion
    -0.06
     коли
    -0.06
    POSITIVE LOGITS
     Empire
    0.16
     empire
    0.14
     Imperial
    0.10
     Reich
    0.09
    perial
    0.08
    帝
    0.08
     immense
    0.07
    帝国
    0.07
     Henry
    0.07
     ή
    0.07
    Activations Density 0.011%

    No Known Activations