© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56355
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron activates on common English stop‐words—especially the definite article “the” (and similar high‐frequency function words like “use” or “new”).

    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
    았다
    -0.08
     celou
    -0.07
     obraz
    -0.07
    ears
    -0.07
     próxima
    -0.06
     reun
    -0.06
    252
    -0.06
    _ij
    -0.06
     цю
    -0.06
     wn
    -0.06
    POSITIVE LOGITS
    prototype
    0.06
     reference
    0.06
    备注
    0.06
    영어
    0.06
     staggering
    0.06
    Control
    0.06
    ーカー
    0.06
     Register
    0.06
    DATABASE
    0.06
    .listen
    0.06
    Activations Density 0.156%

    No Known Activations