© 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. 11-RESID-POST-AA
    6. 87602
    Prev
    Next
    INDEX
    Explanations

    that

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mitigate
    -0.07
    있
    -0.07
     gelecek
    -0.06
     informations
    -0.06
     burial
    -0.06
    $errors
    -0.06
     Resource
    -0.06
     sweet
    -0.06
    .localization
    -0.06
    hud
    -0.06
    POSITIVE LOGITS
    _ABI
    0.07
    anten
    0.07
    Nota
    0.06
    ashire
    0.06
     buffalo
    0.06
    ión
    0.06
    ij
    0.06
     визначення
    0.06
    dialog
    0.06
     c
    0.06
    Activations Density 0.001%

    No Known Activations