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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 631
    Prev
    Next
    INDEX
    Explanations

    property

    np_max-act · gemini-2.0-flash

    The neuron fires on Spring XML `<property>` elements (i.e. on bean-property name/value declarations).

    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
    onaut
    -0.07
     inevitably
    -0.06
     Iz
    -0.06
     Jenkins
    -0.06
     dawn
    -0.06
    jmu
    -0.06
    iode
    -0.06
    ورد
    -0.06
     inventor
    -0.06
    	rs
    -0.06
    POSITIVE LOGITS
    ็ว
    0.07
    .RemoveAt
    0.06
    PARAM
    0.06
    CSS
    0.06
    (update
    0.06
     contin
    0.06
    ((__
    0.06
     pcb
    0.06
    Paint
    0.06
     Lesb
    0.06
    Activations Density 0.001%

    No Known Activations