© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 45000
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron detects technical descriptions of one component being attached or fixed to another (e.g., “affixed to a hub having threads,” “mounted to the case”).

    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
     Tucson
    -0.06
     ("<
    -0.06
    -login
    -0.06
    كة
    -0.06
    _cache
    -0.06
    (colors
    -0.06
     سخت
    -0.06
    /ion
    -0.06
    머니
    -0.06
    atinum
    -0.06
    POSITIVE LOGITS
     определя
    0.07
    _SCHEDULE
    0.07
     Цент
    0.06
    friend
    0.06
    getContext
    0.06
    áte
    0.06
    ра�
    0.06
    ppers
    0.06
    �
    0.06
     though
    0.06
    Activations Density 0.056%

    No Known Activations