© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 111009
    Prev
    Next
    INDEX
    Explanations

    vs

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yolu
    -0.07
    ่ท
    -0.06
    광고
    -0.06
     مشکلات
    -0.06
    うち
    -0.06
    _RSA
    -0.06
    .setdefault
    -0.06
     客
    -0.06
    .write
    -0.06
    imes
    -0.06
    POSITIVE LOGITS
    .NumericUpDown
    0.08
     \
    ↵
    0.07
     Expenses
    0.07
    .appspot
    0.06
     dank
    0.06
     appDelegate
    0.06
    itbart
    0.06
    list
    0.06
     UIButton
    0.06
     ha
    0.06
    Activations Density 0.000%

    No Known Activations