© 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. 73925
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric measurements and dimensions (e.g., lengths, widths, heights, or other numeric specs).

    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
    =i
    -0.07
    IES
    -0.06
    (board
    -0.06
    銀行
    -0.06
     penetrated
    -0.06
    芙
    -0.06
    Inspector
    -0.06
     司
    -0.06
     yaklaş
    -0.06
     Yard
    -0.06
    POSITIVE LOGITS
    ΟΙ
    0.07
    іки
    0.06
    zM
    0.06
     معد
    0.06
    acional
    0.06
     Obrázky
    0.06
    cdr
    0.06
     Khi
    0.06
    ุทธ
    0.06
    _office
    0.06
    Activations Density 0.145%

    No Known Activations