© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8943
    Prev
    Next
    INDEX
    Explanations

    AIDS

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of AIDS or HIV-related syndrome terms (e.g. “AIDS,” “syndrome,” “HIV/AIDS”).

    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
     garage
    -0.08
    People
    -0.07
    Future
    -0.07
    Sun
    -0.07
     January
    -0.07
    �
    -0.07
    Runnable
    -0.07
    Hor
    -0.07
    _b
    -0.06
    Schedule
    -0.06
    POSITIVE LOGITS
     AIDS
    0.12
    /AIDS
    0.07
     milf
    0.07
     ABD
    0.06
     /************************************************************************
    0.06
     &,
    0.06
    -only
    0.06
    .opend
    0.06
     среди
    0.06
     ([[
    0.06
    Activations Density 0.001%

    No Known Activations