© 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. 44415
    Prev
    Next
    INDEX
    Explanations

    inheritance and classes

    np_max-act · gemini-2.0-flash

    This neuron activates on generic type or template parameter declarations and constraints in code (e.g. “<T extends…>,” “IEnumerable<T>,” or ExportAttribute<>).

    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
     Excellence
    -0.06
    روش
    -0.06
     flam
    -0.06
    usi
    -0.06
    rec
    -0.06
     trải
    -0.06
    (avg
    -0.06
    .medium
    -0.06
     شمال
    -0.06
     Autism
    -0.06
    POSITIVE LOGITS
     başka
    0.07
    /dis
    0.07
    Ub
    0.06
    ιο
    0.06
    _Function
    0.06
     исполн
    0.06
    =<
    0.06
    832
    0.06
    .XtraPrinting
    0.06
    _custom
    0.06
    Activations Density 0.024%

    No Known Activations