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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 37211
    Prev
    Next
    INDEX
    Explanations

    stance

    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
     med
    -0.06
     зависимости
    -0.06
    混合
    -0.06
    aturdays
    -0.06
    _dialog
    -0.06
     invocation
    -0.06
     override
    -0.06
    supplier
    -0.06
     Mü
    -0.06
     wildcard
    -0.06
    POSITIVE LOGITS
    逆
    0.07
     position
    0.07
     stance
    0.07
     ascend
    0.06
    阶段
    0.06
    ματος
    0.06
    ΕΤ
    0.06
    ंड
    0.06
    EATURE
    0.06
    可能
    0.06
    Activations Density 0.011%

    No Known Activations