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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21266
    Prev
    Next
    INDEX
    Explanations

    English text snippets

    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
    .Our
    -0.06
    うん
    -0.06
    _Get
    -0.06
    _wo
    -0.06
    ManagedObjectContext
    -0.06
     Womens
    -0.06
    .then
    -0.06
    isRequired
    -0.06
    た
    -0.06
    ーター
    -0.05
    POSITIVE LOGITS
     RVA
    0.06
    .archive
    0.06
    idences
    0.06
    IZED
    0.06
    .metrics
    0.06
     contato
    0.06
     cv
    0.06
    YNAMIC
    0.06
     location
    0.06
    pri
    0.06
    Activations Density 0.000%

    No Known Activations