© 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. 29628
    Prev
    Next
    INDEX
    Explanations

    commune

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “commune,” i.e. when the text labels a place as a French commune.

    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
    itizen
    -0.06
    bau
    -0.06
    ?>">
    -0.06
     kötü
    -0.06
    (_)
    -0.06
    _door
    -0.06
     peuvent
    -0.06
    _picker
    -0.06
    _thumbnail
    -0.06
     klein
    -0.06
    POSITIVE LOGITS
     commune
    0.08
     overload
    0.06
     Colum
    0.06
    几
    0.06
     Engineering
    0.06
     заболевания
    0.06
     Lanka
    0.06
    pector
    0.06
     fungal
    0.06
     özel
    0.06
    Activations Density 0.001%

    No Known Activations