© 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. 57424
    Prev
    Next
    INDEX
    Explanations

    describing circumstances

    np_max-act · gemini-2.0-flash

    This neuron activates on words that report statistical frequency or prevalence (e.g., “found,” “rarely,” “more frequent,” “associated with”).

    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
    Registers
    -0.07
    振
    -0.06
     terminate
    -0.06
    under
    -0.06
    もっと
    -0.06
    umhur
    -0.06
    ыш
    -0.06
     signage
    -0.06
    forced
    -0.06
    iare
    -0.06
    POSITIVE LOGITS
    cone
    0.07
    /Table
    0.06
    ','=',
    0.06
    _TMP
    0.06
    _J
    0.06
    형
    0.06
    xlsx
    0.06
     المنطقة
    0.06
    牛
    0.06
    .Excel
    0.06
    Activations Density 0.090%

    No Known Activations