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. 7-RESID-POST-AA
    6. 10182
    Prev
    Next
    INDEX
    Explanations

    fraud

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ственный
    -0.07
    angan
    -0.07
     الاج
    -0.06
     chú
    -0.06
    ляти
    -0.06
    _slow
    -0.06
     kho
    -0.06
     چرخ
    -0.06
     khí
    -0.06
     zorunlu
    -0.06
    POSITIVE LOGITS
     fraud
    0.11
     Fraud
    0.11
     Obtain
    0.07
    _u
    0.07
    ौर
    0.06
    도가
    0.06
     admit
    0.06
    Orientation
    0.06
     squir
    0.06
    	Print
    0.06
    Activations Density 0.003%

    No Known Activations