© 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
    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. 91340
    Prev
    Next
    INDEX
    Explanations

    Small amounts

    np_max-act · gemini-2.0-flash

    The neuron is keyed to erotic maternal/nursing imagery—references to nursing, wetting, diapers, incontinence, and the mixing of caregiving with sexual content.

    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
     Cos
    -0.06
    .Tween
    -0.06
    FUNC
    -0.06
    ExecutionContext
    -0.06
     ….
    -0.06
    continued
    -0.06
    #================================================================
    -0.06
     Selbst
    -0.05
    _Internal
    -0.05
    Development
    -0.05
    POSITIVE LOGITS
    BIND
    0.07
    icio
    0.06
    nze
    0.06
     захворювання
    0.06
    AXB
    0.06
    .readlines
    0.06
    agg
    0.06
    aminer
    0.06
     perhaps
    0.06
     dre
    0.06
    Activations Density 0.017%

    No Known Activations