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. 87047
    Prev
    Next
    INDEX
    Explanations

    research papers

    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
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bh
    -0.07
     simpler
    -0.07
     سید
    -0.07
    ateful
    -0.07
     rozší
    -0.07
    ,...
    -0.06
    ptal
    -0.06
    �
    -0.06
     emphasize
    -0.06
    (fh
    -0.06
    POSITIVE LOGITS
    atom
    0.06
    -----------*/↵
    0.06
     neredeyse
    0.06
    仪
    0.06
     Added
    0.06
     transaction
    0.06
     Disc
    0.06
     数
    0.06
    廣
    0.06
     مج
    0.06
    Activations Density 0.003%

    No Known Activations