© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 92829
    Prev
    Next
    INDEX
    Explanations

    Math and coding

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     따라
    -0.07
     heartfelt
    -0.06
    äs
    -0.06
    genesis
    -0.06
     وذلك
    -0.06
     obliged
    -0.06
     choix
    -0.06
     constitutional
    -0.06
     dalla
    -0.06
     daha
    -0.06
    POSITIVE LOGITS
     locating
    0.06
    (tv
    0.06
    Dear
    0.06
     alertDialog
    0.06
     resale
    0.06
    inine
    0.06
    $lang
    0.06
    .Style
    0.06
     Information
    0.06
     Ellis
    0.06
    Activations Density 0.001%

    No Known Activations