© 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. 124912
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    The neuron activates on numbered legal citations—statute and rule section references (e.g., “§ 667,” “8.1115(b)”).

    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
    отор
    -0.06
     ประเทศ
    -0.06
    CanBe
    -0.06
     mile
    -0.06
     larg
    -0.06
    _CASE
    -0.06
     kế
    -0.06
    =post
    -0.06
     bề
    -0.06
    ETF
    -0.06
    POSITIVE LOGITS
     Clears
    0.07
    ElementType
    0.06
     wat
    0.06
    ROY
    0.06
    .getOwnProperty
    0.06
    (Activity
    0.06
     Zealand
    0.06
    cube
    0.06
     vent
    0.06
    .rel
    0.06
    Activations Density 0.007%

    No Known Activations