© 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. 68387
    Prev
    Next
    INDEX
    Explanations

    ly

    np_max-act · gemini-2.0-flash

    This neuron picks out tokens containing the “-ly” suffix (e.g. the “ly” in words like “linearly”).

    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
    washing
    -0.06
    orce
    -0.06
     행정
    -0.06
    .store
    -0.06
    _working
    -0.06
     PA
    -0.06
    .spring
    -0.06
     workspace
    -0.06
    essler
    -0.06
    	FILE
    -0.06
    POSITIVE LOGITS
    一区
    0.07
     profoundly
    0.07
     promptly
    0.07
    ainment
    0.06
     hotels
    0.06
     ****************
    0.06
    SQLite
    0.06
    飯
    0.06
     rồi
    0.06
     formations
    0.06
    Activations Density 0.004%

    No Known Activations