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. 11-RESID-POST-AA
    6. 35980
    Prev
    Next
    INDEX
    Explanations

    spying

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    олько
    -0.07
     valido
    -0.06
    Deck
    -0.06
    лот
    -0.06
     ram
    -0.06
     bakery
    -0.06
     Legends
    -0.06
    .fig
    -0.06
    atings
    -0.06
    tiği
    -0.06
    POSITIVE LOGITS
     nonetheless
    0.07
    _recovery
    0.06
     Müdürlüğü
    0.06
    .FileName
    0.06
    INTERN
    0.06
    trand
    0.06
    UBY
    0.06
     ngủ
    0.06
    />↵
    0.06
    .Dispatcher
    0.06
    Activations Density 0.029%

    No Known Activations