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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 126434
    Prev
    Next
    INDEX
    Explanations

    .createElement

    np_max-act · gemini-2.0-flash

    This neuron detects JavaScript code that dynamically creates and inserts external `<script>` tags (e.g. via document.createElement(...), setting `.src`/`.async`, and appending to the DOM).

    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
     Sevilla
    -0.07
    _device
    -0.06
    Atlanta
    -0.06
    acement
    -0.06
    Agency
    -0.06
    Echo
    -0.06
    astery
    -0.06
    .en
    -0.06
     UIL
    -0.06
     Markets
    -0.06
    POSITIVE LOGITS
    /↵↵↵
    0.08
     اضافه
    0.07
     actualizar
    0.07
     *}↵↵
    0.06
    >';
    ↵
    0.06
     mutating
    0.06
    ग
    0.06
     horror
    0.06
    ],[-
    0.06
    선
    0.06
    Activations Density 0.002%

    No Known Activations