© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92439
    Prev
    Next
    INDEX
    Explanations

    churches, saints

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of church buildings and their saint dedications (e.g. “church,” “Saint,” “St.” plus saint names).

    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
    .pag
    -0.07
     lem
    -0.07
    //!
    -0.07
     Kes
    -0.06
    _NB
    -0.06
     rtl
    -0.06
     Urs
    -0.06
     bes
    -0.06
    iber
    -0.06
    arta
    -0.06
    POSITIVE LOGITS
     itertools
    0.07
    ้ย
    0.06
     Portland
    0.06
    戻
    0.06
    patibility
    0.06
    品牌
    0.06
    .RegisterType
    0.06
     aslında
    0.06
    .border
    0.06
     appell
    0.06
    Activations Density 0.022%

    No Known Activations