© 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. 12258
    Prev
    Next
    INDEX
    Explanations

    Sensual

    np_max-act · gemini-2.0-flash

    The neuron activates on descriptive, erotic or sexual-adjacent adjectives (e.g., “lustful,” “nympho,” “sensual”) indicating it’s detecting explicit sexual descriptors.

    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
    違
    -0.07
    reas
    -0.07
    	trace
    -0.06
    -ref
    -0.06
    如果
    -0.06
     casino
    -0.06
     ماشین
    -0.06
     Roch
    -0.06
    "How
    -0.06
     operated
    -0.06
    POSITIVE LOGITS
     sensual
    0.08
    orda
    0.08
     KIND
    0.07
     lush
    0.07
     مم
    0.07
    XL
    0.06
    loon
    0.06
    endra
    0.06
     DPI
    0.06
     overall
    0.06
    Activations Density 0.005%

    No Known Activations