© 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. 92239
    Prev
    Next
    INDEX
    Explanations

    oor

    np_max-act · gemini-2.0-flash

    The neuron strongly responds to numeric expressions—especially numbers with decimal points or measurement figures (e.g. weights, prices, fractional values).

    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
     Scientists
    -0.07
    يري
    -0.06
     RAW
    -0.06
     ([
    -0.06
     نيز
    -0.06
    RESH
    -0.06
     Ui
    -0.06
     đã
    -0.06
    OH
    -0.05
    ên
    -0.05
    POSITIVE LOGITS
    .dumps
    0.07
    .guna
    0.07
    .Receive
    0.07
     المخت
    0.07
    .Route
    0.07
    _spectrum
    0.06
    _UPPER
    0.06
    _super
    0.06
     Bair
    0.06
    invoice
    0.06
    Activations Density 0.580%

    No Known Activations