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. 87052
    Prev
    Next
    INDEX
    Explanations

    JSON/code snippets

    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
    <dyn
    -0.07
     Cycling
    -0.07
    olecular
    -0.06
     ا�
    -0.06
    akers
    -0.06
     pneum
    -0.06
     Smart
    -0.06
    <button
    -0.06
     chained
    -0.06
    cli
    -0.06
    POSITIVE LOGITS
    †
    0.06
     matures
    0.06
    -art
    0.06
    /include
    0.06
    ız
    0.06
     ngon
    0.06
     شکل
    0.05
     araştır
    0.05
     specialists
    0.05
    _DEFAULT
    0.05
    Activations Density 0.013%

    No Known Activations