© 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. 44792
    Prev
    Next
    INDEX
    Explanations

    Wearable tech/clothing

    np_max-act · gemini-2.0-flash

    information related to wearable and flexible technology.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on mentions of cutaneous or tactile feedback technologies/materials (e.g. haptic fabrics, electrotextiles, tactile actuators).

    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
     deliver
    -0.07
    ję
    -0.06
    clare
    -0.06
    σσότε
    -0.06
    Employee
    -0.06
    भ
    -0.06
    His
    -0.06
     unlimited
    -0.06
     Nhân
    -0.06
     сы
    -0.06
    POSITIVE LOGITS
     african
    0.07
     IDisposable
    0.06
    （昭和
    0.06
     inputValue
    0.06
    _radi
    0.06
    \Catalog
    0.06
     pomoc
    0.06
     Continental
    0.06
     yaptık
    0.06
    ’ya
    0.06
    Activations Density 0.208%

    No Known Activations