© 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
    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. 39049
    Prev
    Next
    INDEX
    Explanations

    family

    np_max-act · gemini-2.0-flash

    The neuron detects family‐relation terms (e.g. husband, wife, mother, father) in the text.

    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
    _xx
    -0.07
    ennon
    -0.07
    CLU
    -0.06
    Registr
    -0.06
    /un
    -0.06
     Catalyst
    -0.06
    .gif
    -0.06
    Dragging
    -0.06
     turbulent
    -0.06
     HttpServletRequest
    -0.06
    POSITIVE LOGITS
    (cap
    0.07
     Increases
    0.06
    passes
    0.06
    bottom
    0.06
    wert
    0.06
    !(
    0.06
    ；
    0.06
    ■
    0.06
     thunk
    0.06
     simply
    0.06
    Activations Density 0.007%

    No Known Activations