© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38775
    Prev
    Next
    INDEX
    Explanations

    Get

    np_max-act · gemini-2.0-flash

    The neuron detects promotional calls‐to‐action, i.e. imperative marketing prompts like “Get,” “Save,” “Check,” “Enjoy,” and “Find.”

    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
     Rao
    -0.06
    ublik
    -0.06
     경우
    -0.06
     Everyday
    -0.06
    lovak
    -0.06
     Graduate
    -0.06
     nonlinear
    -0.06
    .website
    -0.06
    Disc
    -0.05
     bloggers
    -0.05
    POSITIVE LOGITS
     dinosaurs
    0.07
    .elapsed
    0.07
    entication
    0.07
     textBox
    0.07
     derp
    0.07
     automat
    0.07
    	settings
    0.07
     vero
    0.06
    ($"
    0.06
    .'
    0.06
    Activations Density 0.013%

    No Known Activations