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. 3-RESID-POST-AA
    6. 122814
    Prev
    Next
    INDEX
    Explanations

    @class

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     روند
    -0.07
     assembler
    -0.06
     mythology
    -0.06
    _demand
    -0.06
     Nếu
    -0.06
    Bei
    -0.06
    Timing
    -0.06
    Warehouse
    -0.06
     Tyto
    -0.06
    Ni
    -0.06
    POSITIVE LOGITS
    @class
    0.16
    =".
    0.10
    enum
    0.07
    bus
    0.07
    emark
    0.07
    Guest
    0.07
    増
    0.07
     Columbus
    0.07
    sg
    0.07
     المعلومات
    0.06
    Activations Density 0.003%

    No Known Activations