© 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. 127104
    Prev
    Next
    INDEX
    Explanations

    download

    np_max-act · gemini-2.0-flash

    The neuron detects Spanish download-related verb forms (e.g., “descarga,” “descargar”).

    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
    质
    -0.07
     perceived
    -0.07
     setValue
    -0.06
     neutrality
    -0.06
    rices
    -0.06
    abella
    -0.06
    柜
    -0.06
    /place
    -0.06
     precios
    -0.06
    Directions
    -0.06
    POSITIVE LOGITS
     capt
    0.07
    ＾
    0.06
     clip
    0.06
     Tiếng
    0.06
    _fw
    0.06
    \Entities
    0.06
    Captain
    0.06
    JP
    0.06
    _tv
    0.06
    ...,
    0.06
    Activations Density 0.015%

    No Known Activations