© 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. 74009
    Prev
    Next
    INDEX
    Explanations

    health risks and bans

    np_max-act · gemini-2.0-flash

    The neuron activates on words that signal safety or health concerns and regulatory scrutiny—terms like concern, scrutiny, led, calls, research, regulatory.

    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
     تبد
    -0.07
    .rate
    -0.06
     dicho
    -0.06
    \Url
    -0.06
    pte
    -0.06
    ogenic
    -0.06
     par
    -0.06
    _asset
    -0.06
     vets
    -0.06
    aciente
    -0.06
    POSITIVE LOGITS
     ян
    0.07
    ///
    ↵
    0.07
    .directive
    0.06
     HELP
    0.06
    webkit
    0.06
    叔
    0.06
    /comments
    0.06
     Took
    0.06
     goalt
    0.06
     Partisi
    0.06
    Activations Density 0.030%

    No Known Activations