© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6925
    Prev
    Next
    INDEX
    Explanations

    economy/market

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to numeric tokens—especially decimal numbers and quantitative figures like interest‐rate values and economic data.

    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
    واهد
    -0.07
    lararası
    -0.06
    clar
    -0.06
    olumes
    -0.06
     Leaves
    -0.06
    करण
    -0.06
    _running
    -0.06
    adığ
    -0.06
    放送
    -0.06
    Think
    -0.06
    POSITIVE LOGITS
     bên
    0.06
     ngọt
    0.06
    ีป
    0.06
     choisir
    0.06
     appropriated
    0.06
     شمالی
    0.06
     Auschwitz
    0.06
    :no
    0.06
    蒂
    0.06
     CHECK
    0.06
    Activations Density 0.019%

    No Known Activations