© 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. 41082
    Prev
    Next
    INDEX
    Explanations

    auf

    np_max-act · gemini-2.0-flash

    The neuron responds to short German function words—especially common prepositions like “auf,” “über,” and “an.”

    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
    Mur
    -0.07
     Mur
    -0.07
    grant
    -0.07
     travelers
    -0.06
     دنی
    -0.06
     kazan
    -0.06
    location
    -0.06
    Say
    -0.06
    DEN
    -0.06
    man
    -0.06
    POSITIVE LOGITS
     auf
    0.09
     naar
    0.08
     für
    0.08
    یشه
    0.07
    Auf
    0.07
    行为
    0.07
     in
    0.07
     At
    0.07
     aynı
    0.07
     섬
    0.07
    Activations Density 0.054%

    No Known Activations