© 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. 110813
    Prev
    Next
    INDEX
    Explanations

    promotional language

    np_max-act · gemini-2.0-flash

    the neuron detects promotional or sales-style hype language—words used to tout or market something as exciting, exclusive, or superior.

    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
    办公
    -0.07
     provision
    -0.07
     trend
    -0.07
    username
    -0.07
     owners
    -0.07
     QA
    -0.07
     spéc
    -0.06
     rifles
    -0.06
    pink
    -0.06
     pä
    -0.06
    POSITIVE LOGITS
    MASConstraintMaker
    0.08
    ----------↵
    0.07
    ">&#
    0.07
     hấp
    0.06
     xcb
    0.06
    (('
    0.06
    ')));↵
    0.06
    ostringstream
    0.06
    _First
    0.06
    _GO
    0.06
    Activations Density 0.103%

    No Known Activations