© 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. 7196
    Prev
    Next
    INDEX
    Explanations

    AdS/CFT correspondence

    np_max-act · gemini-2.0-flash

    This neuron responds to terms referring to Anti-de Sitter space (e.g. “AdS,” “anti-de Sitter”).

    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
     constitutes
    -0.06
    suppress
    -0.06
    む
    -0.06
    External
    -0.06
    abel
    -0.06
    Priority
    -0.06
    important
    -0.06
    istique
    -0.06
    ividual
    -0.06
    category
    -0.06
    POSITIVE LOGITS
    Nit
    0.06
     zinc
    0.06
     Thời
    0.06
    .Back
    0.06
     chơi
    0.06
    _yes
    0.06
    (files
    0.06
    (steps
    0.06
     Stadt
    0.06
     tries
    0.06
    Activations Density 0.001%

    No Known Activations