© 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. 7031
    Prev
    Next
    INDEX
    Explanations

    Titles/Positions

    np_max-act · gemini-2.0-flash

    The neuron activates on words indicating people’s formal roles or titles (e.g. director, investigator, founder, chair, congresswoman).

    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
     and
    -0.08
    票
    -0.07
    ive
    -0.07
     pr
    -0.07
    chner
    -0.07
    аря
    -0.07
    ousands
    -0.07
     methodName
    -0.07
    撃
    -0.06
    .metro
    -0.06
    POSITIVE LOGITS
    ToolBar
    0.06
    .choice
    0.06
    Const
    0.06
    .EventHandler
    0.06
    ContentPane
    0.06
     лицо
    0.06
     Birliği
    0.06
     ภ
    0.06
    CLE
    0.06
    ュー
    0.06
    Activations Density 0.037%

    No Known Activations