© 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. 58247
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash

    This neuron lights up on verbs and phrases that describe experimental methods or study procedures (e.g. “have,” “been studied,” “using,” “examined,” “evaluated”).

    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
     Child
    -0.07
    -0.07
     "<
    -0.06
     frustrating
    -0.06
     GameController
    -0.06
    .tick
    -0.06
    .".
    -0.06
    рии
    -0.06
     Spending
    -0.05
     груз
    -0.05
    POSITIVE LOGITS
    _phy
    0.07
    addColumn
    0.07
    ByEmail
    0.07
     pubb
    0.07
    getUser
    0.07
    _missing
    0.06
     publik
    0.06
     main
    0.06
     št
    0.06
     oversees
    0.06
    Activations Density 0.109%

    No Known Activations