© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 75257
    Prev
    Next
    INDEX
    Explanations

    code 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_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
    尋
    -0.07
    CppObject
    -0.07
    消费
    -0.07
     barren
    -0.07
    _));↵
    -0.06
    ifter
    -0.06
     running
    -0.06
    /cart
    -0.06
     Remain
    -0.06
    روب
    -0.06
    POSITIVE LOGITS
     Sosyal
    0.07
    .dll
    0.07
    .mapbox
    0.06
     Vulkan
    0.06
     corruption
    0.06
     Employ
    0.06
     telecommunications
    0.06
    .getCmp
    0.06
     хорошо
    0.06
    xBF
    0.06
    Activations Density 0.090%

    No Known Activations