© 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. 44741
    Prev
    Next
    INDEX
    Explanations

    web page text

    np_max-act · gemini-2.0-flash

    The neuron flags promotional “call-to-action” language—imperative or marketing slogans inviting the reader to try, discover, find, open, or present something.

    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
    _pkg
    -0.07
    ів
    -0.07
     Mistress
    -0.06
     jehož
    -0.06
    updatedAt
    -0.06
    isplay
    -0.06
    ka
    -0.06
     wind
    -0.06
     Mozart
    -0.06
     gearbox
    -0.06
    POSITIVE LOGITS
     Beaut
    0.07
    UserId
    0.06
     picks
    0.06
     कड
    0.06
    AUT
    0.06
     ऐ
    0.06
     Inspiration
    0.06
     threaded
    0.06
     <|
    0.06
    [in
    0.06
    Activations Density 0.028%

    No Known Activations