© 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. 13826
    Prev
    Next
    INDEX
    Explanations

    speculations about future

    np_max-act · gemini-2.0-flash

    This neuron activates on modal auxiliary verbs expressing possibility or obligation (e.g., “may,” “would,” “should”).

    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
    _buffers
    -0.07
    nova
    -0.06
    iddleware
    -0.06
    /sample
    -0.06
    /student
    -0.06
     buscar
    -0.06
    安排
    -0.06
     motorcycles
    -0.06
    iado
    -0.05
     wanna
    -0.05
    POSITIVE LOGITS
    ()});↵
    0.07
     MEP
    0.06
     ความ
    0.06
     erotica
    0.06
     ماند
    0.06
     вступ
    0.06
     noexcept
    0.06
    .Exists
    0.06
     ADMIN
    0.06
    755
    0.06
    Activations Density 0.069%

    No Known Activations