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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-RESID-POST-AA
    6. 83423
    Prev
    Next
    INDEX
    Explanations

    unrecognizable characters

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    řiv
    -0.08
    ular
    -0.06
     Sunny
    -0.06
     Julian
    -0.06
     simulation
    -0.06
     Nguyễn
    -0.06
     Profiles
    -0.06
    ependency
    -0.06
     Engine
    -0.06
    :Boolean
    -0.06
    POSITIVE LOGITS
     дів
    0.07
    --[
    0.07
    Blake
    0.07
    TW
    0.06
     بازی
    0.06
     Autism
    0.06
    (not
    0.06
    _minute
    0.06
    .Record
    0.06
    ("-",
    0.06
    Activations Density 0.006%

    No Known Activations