© 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. 57391
    Prev
    Next
    INDEX
    Explanations

    middle

    np_max-act · gemini-2.0-flash

    The neuron fires on CSS style declarations—particularly layout and box‐model property values (e.g. display, position, cursor, padding, height, line‐height, 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
    ui
    -0.07
    _saved
    -0.06
     {?
    -0.06
     mont
    -0.06
    Once
    -0.06
    Andy
    -0.06
    usa
    -0.06
     protagonist
    -0.06
     USER
    -0.06
    .aw
    -0.06
    POSITIVE LOGITS
    :center
    0.06
    SENSOR
    0.06
    _INFINITY
    0.06
     STORE
    0.06
     admins
    0.06
     année
    0.06
    );\↵
    0.06
    �
    0.06
     insecurity
    0.06
    .hover
    0.06
    Activations Density 0.023%

    No Known Activations