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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 110352
    Prev
    Next
    INDEX
    Explanations

    <=

    np_max-act · gemini-2.0-flash

    This neuron flags Razor view HTML‐helper expressions (e.g. calls like `@Html.LabelFor`, `@Html.EditorFor`, `@Html.ValidationMessageFor`, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     homogeneous
    -0.07
     Wang
    -0.07
     rozp
    -0.06
    ERP
    -0.06
    REP
    -0.06
    製作
    -0.06
     rempl
    -0.06
     MPC
    -0.06
    epend
    -0.06
    講
    -0.06
    POSITIVE LOGITS
    acha
    0.07
    áb
    0.06
    ()));
    0.06
    ");
    0.06
     voksen
    0.06
     Newly
    0.06
    _condition
    0.06
    .”
    0.06
     aka
    0.06
    .setCancelable
    0.06
    Activations Density 0.002%

    No Known Activations