© 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
    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. 6961
    Prev
    Next
    INDEX
    Explanations

    real estate/gardening

    np_max-act · gemini-2.0-flash

    The neuron detects references to individual land or property parcels (e.g. “lot,” “plot,” “allotment,” “unit,” and related counts).

    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
    Leaks
    -0.08
    Poor
    -0.07
     đau
    -0.07
     Chicken
    -0.06
     cate
    -0.06
    _UTF
    -0.06
    _ship
    -0.06
    оло
    -0.06
    問題
    -0.06
    เตอร
    -0.06
    POSITIVE LOGITS
     виб
    0.06
     【
    0.06
     tüm
    0.06
     quaternion
    0.06
    .gridx
    0.06
     socioeconomic
    0.06
    ("{\"
    0.06
    ()↵
    0.06
     грав
    0.06
    براهيم
    0.06
    Activations Density 0.018%

    No Known Activations