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. 19-RESID-POST-AA
    6. 10427
    Prev
    Next
    INDEX
    Explanations

    Code/Technical Documentation

    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
    Languages
    -0.07
     Foster
    -0.07
     Hopkins
    -0.07
     hoog
    -0.06
     OFFSET
    -0.06
    _ch
    -0.06
     Fellowship
    -0.06
     jurisdiction
    -0.06
     KBS
    -0.06
    нин
    -0.06
    POSITIVE LOGITS
    lenmiş
    0.06
    ει
    0.06
    ním
    0.06
     εμπ
    0.06
     folding
    0.06
    왔다
    0.06
    enci
    0.06
    ίναι
    0.06
    ง
    0.06
    inář
    0.06
    Activations Density 0.261%

    No Known Activations