© 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. 19-RESID-POST-AA
    6. 121683
    Prev
    Next
    INDEX
    Explanations

    Code/file-related

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fwd
    -0.07
     todas
    -0.07
    _boundary
    -0.06
     poo
    -0.06
    slides
    -0.06
    =L
    -0.06
     shorthand
    -0.06
     dog
    -0.06
    (string
    -0.06
     target
    -0.06
    POSITIVE LOGITS
     Carson
    0.08
    umptech
    0.07
    .Reflection
    0.07
     akşam
    0.07
     perme
    0.07
    CellValue
    0.07
    194
    0.07
    674
    0.07
    _opacity
    0.07
    cco
    0.07
    Activations Density 0.099%

    No Known Activations