© 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. 30850
    Prev
    Next
    INDEX
    Explanations

    @Entity

    np_max-act · gemini-2.0-flash

    This neuron fires on Java persistence-annotation lines, primarily spotting JPA entity declarations (e.g. @Entity, @Table, @Id).

    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
    aes
    -0.07
    .Proxy
    -0.06
    GetComponent
    -0.06
    .GetComponent
    -0.06
     kaynak
    -0.06
    yre
    -0.06
    krét
    -0.06
    Intent
    -0.06
     остров
    -0.06
    沿
    -0.06
    POSITIVE LOGITS
     lon
    0.07
    طقة
    0.07
     WRONG
    0.06
     너무
    0.06
     Ninh
    0.06
    ')))
    0.06
    ưới
    0.06
     tougher
    0.06
     communic
    0.06
     Third
    0.06
    Activations Density 0.001%

    No Known Activations