© 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 EvalsExportsinterp-engineNEWAPI 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. 58672
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron fires on abstract, positive “virtue” or value words (e.g. cooperation, tolerance, nurturance, freedom, peace, purity, simplicity, 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
     prosper
    -0.06
    ecimal
    -0.06
    DonaldTrump
    -0.06
    813
    -0.06
     verte
    -0.06
    =df
    -0.06
    (comp
    -0.06
    ازی
    -0.06
     Brook
    -0.06
    _particle
    -0.06
    POSITIVE LOGITS
     حجم
    0.07
     PAT
    0.07
     Kanunu
    0.06
     fatty
    0.06
    ΑΓ
    0.06
     Inf
    0.06
     Дата
    0.06
    erie
    0.06
     setVisible
    0.06
     Species
    0.06
    Activations Density 0.098%

    No Known Activations