© 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. 124758
    Prev
    Next
    INDEX
    Explanations

    RecyclerView

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of RecyclerView and its related identifiers (e.g. class names, adapter, layout IDs), i.e. code tokens specific to RecyclerView usage.

    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
     pur
    -0.08
     Wen
    -0.07
     tone
    -0.07
    -ed
    -0.06
     Paradise
    -0.06
     SA
    -0.06
     tour
    -0.06
    (Arg
    -0.06
     haunting
    -0.06
     bouncing
    -0.06
    POSITIVE LOGITS
     RecyclerView
    0.09
     возраст
    0.08
    lightly
    0.07
     yc
    0.07
     Drink
    0.07
    rol
    0.07
     canoe
    0.07
    _DEVICES
    0.07
    ِه
    0.07
    boxes
    0.07
    Activations Density 0.001%

    No Known Activations