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. 53209
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     ออนไลน
    -0.07
    @↵↵
    -0.06
     зд
    -0.06
    、『
    -0.06
     washing
    -0.06
     Dx
    -0.06
     обязатель
    -0.06
    植物
    -0.06
     Німеч
    -0.06
     yapıl
    -0.06
    POSITIVE LOGITS
    damn
    0.07
     psychic
    0.06
     postfix
    0.06
    ıy
    0.06
     nez
    0.06
    AdapterFactory
    0.06
     corps
    0.06
    unities
    0.06
     inevitable
    0.06
     corrid
    0.06
    Activations Density 0.007%

    No Known Activations