© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 20048
    Prev
    Next
    INDEX
    Explanations

    exceptions

    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
    CREMENT
    -0.07
    .↵↵↵↵
    -0.07
     chữ
    -0.06
     yatır
    -0.06
    (output
    -0.06
    /read
    -0.06
    ảnh
    -0.06
     technicians
    -0.06
    .handler
    -0.06
     //!<
    -0.06
    POSITIVE LOGITS
    DOM
    0.07
     FIFA
    0.06
    ceb
    0.06
     Час
    0.06
    ERCHANT
    0.06
     Assign
    0.06
    ي
    0.06
    depending
    0.06
     JAN
    0.06
     Tempo
    0.06
    Activations Density 0.004%

    No Known Activations