© 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 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. 56825
    Prev
    Next
    INDEX
    Explanations

    EF

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of Object–Relational Mapping libraries or ORM frameworks (e.g. “EF”, “ORM”, “Object-Relational Mapper”).

    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
    Inputs
    -0.06
    眼
    -0.06
     Brain
    -0.06
     پخش
    -0.06
    yclerview
    -0.06
     kanıt
    -0.06
     Vaccine
    -0.06
    Skipping
    -0.06
     نمونه
    -0.06
     Thread
    -0.06
    POSITIVE LOGITS
     quantitative
    0.07
    odings
    0.07
    ّ
    0.07
    PID
    0.06
    inson
    0.06
     deviceId
    0.06
    (fr
    0.06
     prt
    0.06
    ATIC
    0.06
     captions
    0.06
    Activations Density 0.024%

    No Known Activations