Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 111119
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [u
    -0.07
    .Identifier
    -0.07
    estyle
    -0.06
    .yellow
    -0.06
    Jar
    -0.06
    (UI
    -0.06
     LinkedList
    -0.06
    irus
    -0.06
    igrams
    -0.06
     Kush
    -0.06
    POSITIVE LOGITS
    keiten
    0.06
    τε
    0.06
     somebody
    0.06
    アルバ
    0.06
    ")]↵↵
    0.06
     friend
    0.06
    РА
    0.05
    //*[
    0.05
    ْم
    0.05
     ekonom
    0.05
    Activations Density 0.065%

    No Known Activations