Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 118371
    Prev
    Next
    INDEX
    Explanations

    Optimum/maximum

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ่ก
    -0.08
     prisons
    -0.07
     serialVersionUID
    -0.07
    输出
    -0.06
    downloads
    -0.06
    ÔNG
    -0.06
     attire
    -0.06
    ρθ
    -0.06
    _old
    -0.06
    _food
    -0.06
    POSITIVE LOGITS
    uin
    0.07
     Akron
    0.07
     vyžad
    0.06
     khác
    0.06
    Standard
    0.06
     Wyoming
    0.06
    ाप
    0.06
     Flyers
    0.06
    播放
    0.06
    acid
    0.06
    Activations Density 0.064%

    No Known Activations