© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 42524
    Prev
    Next
    INDEX
    Explanations

    code functions

    np_max-act · gemini-2.0-flash

    This neuron fires on C++ code syntax elements (e.g. #include, std::thread, join, main, function definitions).

    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
    모
    -0.08
     han
    -0.07
     locks
    -0.07
    uples
    -0.07
    feat
    -0.07
     broke
    -0.06
    炮
    -0.06
    lem
    -0.06
     hed
    -0.06
     epic
    -0.06
    POSITIVE LOGITS
    adjust
    0.07
    allah
    0.07
    tuğ
    0.06
     OleDb
    0.06
    สาย
    0.06
     Bicycle
    0.06
    τικές
    0.06
    respons
    0.06
    decorators
    0.06
     bored
    0.06
    Activations Density 0.034%

    No Known Activations