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. 87079
    Prev
    Next
    INDEX
    Explanations

    GitHub

    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
    IONS
    -0.07
     giriş
    -0.06
    ITTE
    -0.06
     пери
    -0.06
    _ABC
    -0.06
    /contact
    -0.06
     dětí
    -0.06
     kali
    -0.06
    licht
    -0.06
     Carey
    -0.06
    POSITIVE LOGITS
    .isRequired
    0.07
     seasoned
    0.07
    (template
    0.06
     supplying
    0.06
    Positions
    0.06
     enterprise
    0.06
    	Description
    0.06
    SizeMode
    0.06
    Nonnull
    0.06
     serving
    0.06
    Activations Density 0.013%

    No Known Activations