© 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. 39085
    Prev
    Next
    INDEX
    Explanations

    methods, accounting for factors

    np_max-act · gemini-2.0-flash

    The neuron activates on terms that quantify model complexity—particularly words like “number,” “parameters,” and “complexity” in statistical model descriptions.

    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
     nabízí
    -0.06
     "";↵
    -0.06
    .pagination
    -0.06
     impeccable
    -0.06
     gd
    -0.06
    ابد
    -0.06
     得
    -0.06
    	keys
    -0.06
    .TestTools
    -0.06
     तर
    -0.06
    POSITIVE LOGITS
    528
    0.07
     özellik
    0.06
    525
    0.06
    224
    0.06
    -CS
    0.06
     وش
    0.06
     prince
    0.06
    价值
    0.06
    -question
    0.06
    ANGER
    0.06
    Activations Density 0.038%

    No Known Activations