© 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. 56328
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron fires on the capitalized word “The,” as it appears at the start of the copyright notice in license headers.

    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
    ounder
    -0.06
    .currentTime
    -0.06
     declares
    -0.06
    setImage
    -0.06
     Alias
    -0.06
    swagger
    -0.06
     Arth
    -0.06
    quiry
    -0.06
    <<<
    -0.06
    linkedin
    -0.06
    POSITIVE LOGITS
     щ
    0.07
     vig
    0.06
     kne
    0.06
    _;
    ↵
    0.06
     anom
    0.06
     Payment
    0.06
    侵
    0.06
    .showMessage
    0.06
     Bett
    0.06
    -${
    0.06
    Activations Density 0.001%

    No Known Activations