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. 75555
    Prev
    Next
    INDEX
    Explanations

    source and supply

    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
    اصل
    -0.06
    Min
    -0.06
     cambio
    -0.06
    'eau
    -0.06
    .watch
    -0.06
     ministry
    -0.06
    での
    -0.06
    _members
    -0.06
    Entity
    -0.06
    useRal
    -0.06
    POSITIVE LOGITS
     muito
    0.07
    hões
    0.07
    FXML
    0.07
     запас
    0.06
    clado
    0.06
    Raster
    0.06
    VEN
    0.06
    shared
    0.06
     convention
    0.06
     Conte
    0.06
    Activations Density 0.032%

    No Known Activations