© 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. 108895
    Prev
    Next
    INDEX
    Explanations

    ree

    np_max-act · gemini-2.0-flash

    This neuron activates on Portuguese imperative‐mood verbs marking steps in instructions (e.g. “Crie,” “Insira,” “Siga,” “Adicione,” “Coloque”).

    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
    /browser
    -0.06
    Lisa
    -0.06
     ขนาด
    -0.06
    ैल
    -0.06
    _esc
    -0.06
    )||
    -0.06
     nhựa
    -0.06
    _similarity
    -0.06
    (filters
    -0.06
    Audit
    -0.06
    POSITIVE LOGITS
     slopes
    0.07
     [~,
    0.07
     favors
    0.07
    apl
    0.06
    상
    0.06
     canine
    0.06
    Gal
    0.06
    _categoria
    0.06
    be
    0.06
    и
    0.06
    Activations Density 0.067%

    No Known Activations