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. 11-RESID-POST-AA
    6. 104090
    Prev
    Next
    INDEX
    Explanations

    The

    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
    麗
    -0.08
     Treasurer
    -0.07
    ogle
    -0.07
     раб
    -0.07
    ือก
    -0.07
     moon
    -0.06
     само
    -0.06
     melt
    -0.06
     pickups
    -0.06
    adoras
    -0.06
    POSITIVE LOGITS
     멀
    0.07
     hentai
    0.06
     getString
    0.06
    #elif
    0.06
    _user
    0.06
    _mass
    0.06
     buddies
    0.06
    _skills
    0.05
    .getTransaction
    0.05
    cross
    0.05
    Activations Density 0.012%

    No Known Activations