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. 87107
    Prev
    Next
    INDEX
    Explanations

    GL

    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
     getValue
    -0.07
     pg
    -0.06
    504
    -0.06
    (dp
    -0.06
    持ち
    -0.06
    Dam
    -0.05
     mushroom
    -0.05
     mapView
    -0.05
     LPARAM
    -0.05
    contin
    -0.05
    POSITIVE LOGITS
     사업
    0.07
     πιο
    0.07
     ADMIN
    0.07
     norsk
    0.07
    ProductId
    0.07
    İN
    0.07
    hk
    0.07
    inctions
    0.06
     Clark
    0.06
    bounds
    0.06
    Activations Density 0.408%

    No Known Activations