© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 40977
    Prev
    Next
    INDEX
    Explanations

    HIV

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of HIV/AIDS and associated medical treatment or virological terms.

    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
     зміст
    -0.06
     passenger
    -0.06
    bomb
    -0.06
     "_
    -0.06
     tùy
    -0.06
     DAR
    -0.06
     '_
    -0.06
     (_
    -0.06
     spectators
    -0.06
     monks
    -0.06
    POSITIVE LOGITS
    _TEMP
    0.07
    .Information
    0.07
    .gui
    0.07
     HIV
    0.07
     Resist
    0.06
    から
    0.06
    uish
    0.06
    Information
    0.06
    ultureInfo
    0.06
     prat
    0.06
    Activations Density 0.003%

    No Known Activations