© 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. 129968
    Prev
    Next
    INDEX
    Explanations

    new words

    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
     observer
    -0.06
     splitting
    -0.06
    無
    -0.06
    "My
    -0.06
     Kos
    -0.06
    dato
    -0.06
     Vil
    -0.06
     originates
    -0.06
     Observer
    -0.06
    .getID
    -0.06
    POSITIVE LOGITS
    uing
    0.07
    idd
    0.06
    χία
    0.06
    orrar
    0.06
    팅
    0.06
    ovaná
    0.06
     Beste
    0.06
    าท
    0.06
    584
    0.06
     oxid
    0.06
    Activations Density 0.013%

    No Known Activations