© 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. 127176
    Prev
    Next
    INDEX
    Explanations

    sex

    np_max-act · gemini-2.0-flash

    The neuron flags words appearing in legal non-discrimination statements, especially terms naming protected categories (e.g. sex, race, disability, etc.).

    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
     shl
    -0.07
    -
    -0.07
    '&&
    -0.07
     srd
    -0.06
    DAO
    -0.06
    acht
    -0.06
    RAL
    -0.06
    #####↵
    -0.06
     Between
    -0.06
    _Al
    -0.06
    POSITIVE LOGITS
     alleging
    0.06
    _pedido
    0.06
    وئ
    0.06
    .control
    0.06
     Ph
    0.06
     توص
    0.06
    Ћ
    0.06
     ط
    0.06
    Boundary
    0.06
    -status
    0.06
    Activations Density 0.003%

    No Known Activations