© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 107224
    Prev
    Next
    INDEX
    Explanations

    Comparisons or contrasts

    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
    悪
    -0.07
     useRouter
    -0.06
    کاری
    -0.06
     storing
    -0.06
    iffany
    -0.06
     recorded
    -0.06
     People
    -0.06
    Thomas
    -0.06
    ornings
    -0.06
     Keeps
    -0.06
    POSITIVE LOGITS
    CppClass
    0.07
     cuer
    0.07
     prodej
    0.07
     yytype
    0.06
    (bounds
    0.06
     JDBC
    0.06
    UARIO
    0.06
    ixer
    0.06
    //---------------------------------------------------------------------------↵↵
    0.06
     SEXP
    0.06
    Activations Density 0.085%

    No Known Activations