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. 102916
    Prev
    Next
    INDEX
    Explanations

    emphasizing high standards

    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
    masına
    -0.06
     OpenGL
    -0.06
    \uc
    -0.06
     Barcode
    -0.06
    丽
    -0.06
    interesting
    -0.06
    .readlines
    -0.06
    /New
    -0.06
    .rooms
    -0.06
    Range
    -0.06
    POSITIVE LOGITS
     ej
    0.07
     имя
    0.07
    otted
    0.07
    して
    0.06
    abal
    0.06
     Jeremy
    0.06
    олов
    0.06
     decir
    0.06
     Gerr
    0.06
    arked
    0.06
    Activations Density 0.012%

    No Known Activations