Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 53740
    Prev
    Next
    INDEX
    Explanations

    not

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chơi
    -0.07
     deployment
    -0.07
     realizado
    -0.07
     dosage
    -0.06
    _IE
    -0.06
     اجرا
    -0.06
     Τε
    -0.06
    นน
    -0.06
     Ön
    -0.06
    Important
    -0.06
    POSITIVE LOGITS
     not
    0.08
    modal
    0.07
    really
    0.07
    買
    0.06
    альном
    0.06
    (ord
    0.06
     Not
    0.06
    都不
    0.06
    ottle
    0.06
     lacked
    0.06
    Activations Density 0.026%

    No Known Activations