© 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. 128402
    Prev
    Next
    INDEX
    Explanations

    code related

    np_max-act · gemini-2.0-flash

    This neuron activates on fragments of the JPA “Parameter” type name (e.g. “J”, “pa”, “Parameter”), effectively detecting mentions of the JPA Parameter class.

    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
    ]-$
    -0.07
     L
    -0.07
    			
↵			
↵
    -0.06
    theorem
    -0.06
    ocratic
    -0.06
    ottom
    -0.06
    ující
    -0.06
    HeaderInSection
    -0.06
    really
    -0.06
    εβ
    -0.06
    POSITIVE LOGITS
     invol
    0.07
    rně
    0.07
     Bridges
    0.07
     sobě
    0.06
    _DECL
    0.06
    SMART
    0.06
    suma
    0.06
     Frontier
    0.06
     Scre
    0.06
    AVAILABLE
    0.06
    Activations Density 0.043%

    No Known Activations