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. 87019
    Prev
    Next
    INDEX
    Explanations

    Math/formatting characters

    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
    ifecycle
    -0.07
    !”
    -0.07
    .***
    -0.07
    _stride
    -0.06
    calls
    -0.06
    فع
    -0.06
    aines
    -0.06
    為
    -0.06
    Both
    -0.06
    ارا
    -0.06
    POSITIVE LOGITS
     getCurrent
    0.07
    _rem
    0.07
     qry
    0.07
     Elasticsearch
    0.06
    allele
    0.06
    뷰
    0.06
     scalp
    0.06
    (lines
    0.06
    _pet
    0.06
     přítom
    0.06
    Activations Density 0.025%

    No Known Activations