© 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. 52715
    Prev
    Next
    INDEX
    Explanations

    water

    np_max-act · gemini-2.0-flash

    This neuron activates on terms related to municipal water infrastructure (e.g. water systems, mains, treatment plants, towers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to municipal or community water management issues.

    oai_token-act-pair · gpt-4o-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
     ف
    -0.07
    679
    -0.07
    ADOW
    -0.07
    /how
    -0.07
    @d
    -0.06
     кры
    -0.06
    nun
    -0.06
    OTHER
    -0.06
    تد
    -0.06
     Har
    -0.06
    POSITIVE LOGITS
     kitap
    0.06
    (unit
    0.06
    Advertisement
    0.06
    γε
    0.06
    .Cart
    0.06
    _xpath
    0.06
     작
    0.06
     noss
    0.06
     ас
    0.06
    //================================================
    0.06
    Activations Density 0.008%

    No Known Activations