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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 123730
    Prev
    Next
    INDEX
    Explanations

    Negation

    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
     Runner
    -0.06
    -console
    -0.06
     GLFW
    -0.06
     такий
    -0.06
    acie
    -0.06
     builders
    -0.06
    /schema
    -0.06
     permits
    -0.06
    DataRow
    -0.06
    ﺔ
    -0.06
    POSITIVE LOGITS
    Intermediate
    0.07
     هج
    0.06
    amentos
    0.06
     transition
    0.06
     Transition
    0.06
     proje
    0.06
     Responses
    0.06
     ------------
    0.06
    ثير
    0.06
     فت
    0.06
    Activations Density 0.366%

    No Known Activations