© 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. 11-RESID-POST-AA
    6. 87861
    Prev
    Next
    INDEX
    Explanations

    ish

    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
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orient
    -0.07
     Jiang
    -0.07
     Кра
    -0.07
    hů
    -0.06
     Corona
    -0.06
     Yosemite
    -0.06
     Pere
    -0.06
     Đề
    -0.06
     Toni
    -0.06
    زب
    -0.06
    POSITIVE LOGITS
     Scotland
    0.09
     Edinburgh
    0.07
     Scottish
    0.07
    Leod
    0.07
     dieses
    0.07
    ellan
    0.06
     wee
    0.06
    itably
    0.06
    (Unit
    0.06
    icals
    0.06
    Activations Density 0.049%

    No Known Activations