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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 110763
    Prev
    Next
    INDEX
    Explanations

    это

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _points
    -0.07
    629
    -0.06
     addUser
    -0.06
    -on
    -0.06
     pockets
    -0.06
     왕
    -0.06
    dark
    -0.06
     Dương
    -0.06
    _pub
    -0.06
     рівень
    -0.06
    POSITIVE LOGITS
     است
    0.08
     ГО
    0.07
    EIF
    0.07
     Это
    0.07
    існо
    0.07
    iese
    0.07
    Это
    0.07
    /cop
    0.07
     وهي
    0.07
    IMIZE
    0.07
    Activations Density 0.011%

    No Known Activations