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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27226
    Prev
    Next
    INDEX
    Explanations

    models

    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
     farms
    -0.07
     Pill
    -0.07
     ам
    -0.07
     以
    -0.07
     علیه
    -0.06
     Pair
    -0.06
     prostřednictvím
    -0.06
    =dict
    -0.06
    competitive
    -0.06
    {↵↵↵
    -0.06
    POSITIVE LOGITS
     Laud
    0.07
    -trigger
    0.06
     gim
    0.06
    arms
    0.06
     blí
    0.06
    号
    0.06
    ัณฑ
    0.06
    ламент
    0.06
    HeaderView
    0.06
    (book
    0.06
    Activations Density 0.139%

    No Known Activations