© 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. 56707
    Prev
    Next
    INDEX
    Explanations

    neighbors and others

    np_max-act · gemini-2.0-flash

    This neuron fires on words that introduce or carry moral commands or prescriptive statements (e.g. “Do,” “Love,” “Commandments,” “ethical”).

    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
    .gradient
    -0.07
    paste
    -0.06
     mars
    -0.06
     Edison
    -0.06
    ename
    -0.06
    الث
    -0.06
     relig
    -0.06
    .Any
    -0.06
     iss
    -0.06
    سیون
    -0.06
    POSITIVE LOGITS
    人民
    0.08
     ----------------------------------------------------------------------------------------------------------------
    0.06
    _members
    0.06
    рід
    0.06
    ('')↵
    0.06
    clr
    0.06
    (NULL
    0.06
    Bitcoin
    0.06
    .money
    0.06
    ecx
    0.06
    Activations Density 0.025%

    No Known Activations