© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 108841
    Prev
    Next
    INDEX
    Explanations

    под

    np_max-act · gemini-2.0-flash

    The neuron fires on the Russian Cyrillic prefix “под” (as in words like “подлинными,” “подбор,” “подготовку,” etc.).

    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
     confusion
    -0.07
     assemblies
    -0.07
     from
    -0.07
     اختصاص
    -0.06
     rash
    -0.06
     hemorrh
    -0.06
    -bl
    -0.06
    _boxes
    -0.06
    393
    -0.06
     extent
    -0.06
    POSITIVE LOGITS
     под
    0.09
    Pedido
    0.08
     подоб
    0.07
     Pod
    0.07
     під
    0.07
     underground
    0.07
     downtown
    0.07
     Pussy
    0.07
     piger
    0.07
     Bought
    0.07
    Activations Density 0.010%

    No Known Activations