© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30620
    Prev
    Next
    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash

    This neuron detects the signature `<script>` tags specifying JavaScript (i.e. occurrences of `type="text/javascript"` in script elements).

    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
    ‌شده
    -0.07
     Contact
    -0.07
    .fb
    -0.06
     відріз
    -0.06
     свойства
    -0.06
    umno
    -0.06
     Vulkan
    -0.06
    assets
    -0.06
    .patient
    -0.06
    UIAlertAction
    -0.06
    POSITIVE LOGITS
     ade
    0.06
     зах
    0.06
    ric
    0.06
    .numberOfLines
    0.06
     слу
    0.06
    .isFile
    0.06
    lac
    0.06
    phans
    0.06
    .decrypt
    0.06
     SENT
    0.06
    Activations Density 0.001%

    No Known Activations