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. 15-RESID-POST-AA
    6. 111155
    Prev
    Next
    INDEX
    Explanations

    categorization

    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
     Да
    -0.06
     культуры
    -0.06
    disposing
    -0.06
     dolu
    -0.06
     confront
    -0.06
    تل
    -0.06
    761
    -0.06
    .circular
    -0.06
    ิ์
    -0.06
     slaughtered
    -0.06
    POSITIVE LOGITS
    'un
    0.07
     Prel
    0.06
     Announcement
    0.06
    ));
    0.06
    );\
    0.06
    anim
    0.06
     undermined
    0.06
    ulling
    0.06
    литель
    0.06
    >Add
    0.06
    Activations Density 0.280%

    No Known Activations