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. 87099
    Prev
    Next
    INDEX
    Explanations

    English

    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
    ीन
    -0.07
     appending
    -0.07
    fabs
    -0.06
    omb
    -0.06
    Request
    -0.06
    .REQUEST
    -0.06
     어머니
    -0.06
    Kal
    -0.06
    War
    -0.06
    ammed
    -0.06
    POSITIVE LOGITS
     quit
    0.07
     фах
    0.07
    oth
    0.07
    iedy
    0.07
     presenting
    0.06
     имя
    0.06
     Portable
    0.06
     Playground
    0.06
     slur
    0.06
     dehydration
    0.06
    Activations Density 0.002%

    No Known Activations