© 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. 45053
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash

    This neuron responds to incest-style erotic language, particularly “mommy/child” sexual roleplay.

    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
    arsimp
    -0.06
     wired
    -0.06
    =name
    -0.06
    [code
    -0.06
    *dx
    -0.06
    �
    -0.06
     Tiếng
    -0.06
     mais
    -0.06
    ::~
    -0.05
     verir
    -0.05
    POSITIVE LOGITS
     Alleg
    0.08
    Le
    0.07
     communist
    0.06
    glass
    0.06
    Fra
    0.06
    Techn
    0.06
     Cork
    0.06
     intoler
    0.06
    mo
    0.06
    stress
    0.06
    Activations Density 0.042%

    No Known Activations