© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57844
    Prev
    Next
    INDEX
    Explanations

    nozzle

    np_max-act · gemini-2.0-flash

    This neuron detects technical references to fluid‐dispensing openings—especially words like “nozzle” and “orifice” in patent descriptions.

    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
    Cat
    -0.07
    -pad
    -0.06
     Ef
    -0.06
     слов
    -0.06
     Pawn
    -0.06
    PAT
    -0.06
     XF
    -0.06
     Pad
    -0.06
     gim
    -0.06
    posta
    -0.06
    POSITIVE LOGITS
     nozzle
    0.11
     Particip
    0.07
     designated
    0.07
     throttle
    0.07
     jitter
    0.07
    util
    0.07
     국
    0.06
     supplying
    0.06
     zmq
    0.06
     directing
    0.06
    Activations Density 0.002%

    No Known Activations