© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 8328
    Prev
    Next
    INDEX
    Explanations

    import

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     figured
    -0.07
     epsilon
    -0.07
    jícím
    -0.07
     Sr
    -0.07
     Mod
    -0.07
    .minutes
    -0.07
    _agents
    -0.06
     network
    -0.06
     tutoring
    -0.06
    perfect
    -0.06
    POSITIVE LOGITS
     Governments
    0.07
    _SEND
    0.06
    Baş
    0.06
     academia
    0.06
    олож
    0.06
    άν
    0.06
    _POSTFIELDS
    0.06
     dựng
    0.06
     PER
    0.06
     UserControl
    0.06
    Activations Density 0.006%

    No Known Activations