© 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. 57329
    Prev
    Next
    INDEX
    Explanations

    dose

    np_max-act · gemini-2.0-flash

    The neuron activates on quantitative pharmacokinetic details—numerical dose, time, and unit expressions (e.g. “after a single oral dose of 20 mg/kg”).

    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
    ۱۳
    -0.07
     допомоги
    -0.07
     flats
    -0.07
     cabinet
    -0.06
     vigilant
    -0.06
    (sin
    -0.06
    '↵
    -0.06
    ._↵
    -0.06
    _chart
    -0.06
    001
    -0.06
    POSITIVE LOGITS
    _deck
    0.07
     쉽
    0.06
    ushort
    0.06
    absolute
    0.06
     Hüs
    0.06
     enjoyment
    0.06
    _Syntax
    0.06
    /comments
    0.06
    (IR
    0.06
    _tip
    0.06
    Activations Density 0.021%

    No Known Activations