© 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. 7655
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    np_max-act · gemini-2.0-flash

    The neuron activates on technical, quantitative terms describing operational metrics (e.g. data, usage, flow, occupancy) in the context of parking systems.

    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
     ProgressBar
    -0.07
    ุม
    -0.06
    kem
    -0.06
     kdy
    -0.06
    bones
    -0.06
     Sheldon
    -0.06
    下来
    -0.06
     en
    -0.06
    bei
    -0.06
    Marshal
    -0.06
    POSITIVE LOGITS
     "('
    0.07
     toastr
    0.07
     ＜
    0.06
    ТО
    0.06
    一点
    0.06
     заболевания
    0.06
     neut
    0.06
     intel
    0.06
    اتر
    0.06
    UNIT
    0.06
    Activations Density 0.179%

    No Known Activations