© 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. 124837
    Prev
    Next
    INDEX
    Explanations

    physics simulations

    np_max-act · gemini-2.0-flash

    This neuron fires on specialized technical phrases describing fluid–structure or multiphase interface interactions (e.g. “fluid–structure interaction,” “free-surface motion,” “interface dynamics,” “two-phase flows”).

    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
     Lyme
    -0.07
     Lear
    -0.07
     Rowling
    -0.07
    Tonight
    -0.06
    ond
    -0.06
     dof
    -0.06
    (users
    -0.06
     Voj
    -0.06
    scheduler
    -0.06
    _GRAY
    -0.06
    POSITIVE LOGITS
     Obesity
    0.06
     racks
    0.06
    uke
    0.06
    ormsg
    0.06
    理论
    0.06
     acheter
    0.06
     scent
    0.06
     zru
    0.06
     inadvertently
    0.06
    _profit
    0.06
    Activations Density 0.021%

    No Known Activations