© 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. 42888
    Prev
    Next
    INDEX
    Explanations

    mayor

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on occurrences of the word “mayor” (and its plural), i.e. references to someone holding a mayoral office.

    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
     univerz
    -0.07
    ρος
    -0.07
    خواست
    -0.07
    дам
    -0.06
    ровод
    -0.06
    	container
    -0.06
    ازل
    -0.06
     '_',
    -0.06
    르는
    -0.06
    ';↵↵↵↵
    -0.06
    POSITIVE LOGITS
     mayor
    0.12
     Mayor
    0.11
    Mayor
    0.11
     Lt
    0.07
     MJ
    0.07
    _ABI
    0.07
    Dao
    0.07
     Drinks
    0.06
     Forty
    0.06
    ″E
    0.06
    Activations Density 0.013%

    No Known Activations