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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39072
    Prev
    Next
    INDEX
    Explanations

    32

    np_max-act · gemini-2.0-flash

    The neuron fires on C/C++ preprocessor conditionals that check for target platforms or environment macros (e.g. defined(_WIN32), defined(__unix__), WIN32, __APPLE__, 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
     từng
    -0.07
     tabBar
    -0.07
    资产
    -0.06
     <->
    -0.06
     CAS
    -0.06
    ',{
    -0.06
     알고
    -0.06
    洋
    -0.06
    Vous
    -0.06
    /ros
    -0.06
    POSITIVE LOGITS
     ubic
    0.07
    换
    0.07
     Knee
    0.06
    нима
    0.06
    Entr
    0.06
    ouro
    0.06
    eler
    0.06
     inclus
    0.06
     espan
    0.06
     Schedule
    0.06
    Activations Density 0.002%

    No Known Activations