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. 15-RESID-POST-AA
    6. 14805
    Prev
    Next
    INDEX
    Explanations

    History and loss of time

    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
     obedient
    -0.07
    hof
    -0.07
    _dict
    -0.07
    highest
    -0.07
     RTC
    -0.06
     quizzes
    -0.06
    ►
    -0.06
    .println
    -0.06
     küçük
    -0.06
    LOCAL
    -0.06
    POSITIVE LOGITS
     Sap
    0.07
    quez
    0.07
    iển
    0.07
    omor
    0.07
    kového
    0.06
     Haupt
    0.06
    eworthy
    0.06
    otron
    0.06
     Cran
    0.06
    epam
    0.06
    Activations Density 0.038%

    No Known Activations