© 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. 5869
    Prev
    Next
    INDEX
    Explanations

    cushion

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of padding or cushioning (e.g., “table pad(s),” “cushioned,” “padded”).

    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
    homepage
    -0.07
     الخاصة
    -0.06
    ASCADE
    -0.06
    末
    -0.06
    .re
    -0.06
     TestCase
    -0.06
    _BL
    -0.06
    mites
    -0.06
    _FINAL
    -0.06
    .TestCase
    -0.06
    POSITIVE LOGITS
     cushion
    0.12
     cushions
    0.09
     uphol
    0.08
     Cush
    0.08
    JPEG
    0.07
     cush
    0.07
    _gpio
    0.07
    azon
    0.07
     padded
    0.07
    Produ
    0.07
    Activations Density 0.002%

    No Known Activations