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. 75364
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    dis
    -0.06
    ![↵
    -0.06
     BUS
    -0.06
     πρα
    -0.06
     Crypto
    -0.06
    417
    -0.06
     усл
    -0.06
     REGISTER
    -0.06
     Norris
    -0.06
    true
    -0.05
    POSITIVE LOGITS
     eğitim
    0.07
     quiero
    0.07
     ImVec
    0.06
     خلف
    0.06
     подой
    0.06
     browsing
    0.06
     jinak
    0.06
     naar
    0.06
    $class
    0.06
     Baltimore
    0.06
    Activations Density 0.024%

    No Known Activations