© 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. 58780
    Prev
    Next
    INDEX
    Explanations

    Titles of creative works

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of a work’s “eponymous” or titular subject (e.g., the word “eponymous”).

    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
    -ag
    -0.07
     managerial
    -0.07
    .lower
    -0.06
    ASTER
    -0.06
     strong
    -0.06
     Ingredients
    -0.06
    _inputs
    -0.06
    _bbox
    -0.06
    _LOCAL
    -0.06
    nější
    -0.06
    POSITIVE LOGITS
     Tel
    0.07
    (vo
    0.06
     шп
    0.06
     wp
    0.06
     reste
    0.06
     غير
    0.06
     ket
    0.06
     Bis
    0.06
    DEN
    0.06
    م
    0.06
    Activations Density 0.003%

    No Known Activations