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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 54342
    Prev
    Next
    INDEX
    Explanations

    novel

    np_max-act · gemini-2.0-flash

    This neuron flags mentions of “novel” in genre labels—especially “visual novel” or “light novel.”

    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
    ạng
    -0.07
    teří
    -0.07
    /ml
    -0.07
     kole
    -0.07
    stří
    -0.06
    _MOUSE
    -0.06
     zaj
    -0.06
     अप
    -0.06
     seizure
    -0.06
    /tag
    -0.06
    POSITIVE LOGITS
     rugby
    0.06
    populate
    0.06
    :"",↵
    0.06
    βε
    0.06
     perd
    0.06
    elial
    0.06
    urban
    0.06
     adipisicing
    0.06
     {}",
    0.06
    انو
    0.06
    Activations Density 0.003%

    No Known Activations