© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 66599
    Prev
    Next
    INDEX
    Explanations

    pensions and government liabilities

    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
    Stopped
    -0.08
     публі
    -0.07
    άρ
    -0.07
     pavement
    -0.06
    Quiet
    -0.06
     Document
    -0.06
    Minor
    -0.06
    _spectrum
    -0.06
    lements
    -0.06
     interviewed
    -0.06
    POSITIVE LOGITS
     Api
    0.06
    欣
    0.06
     اجازه
    0.06
     образ
    0.06
    �
    0.06
     facade
    0.06
    ViewInit
    0.06
    Před
    0.06
     Vand
    0.06
     :.
    0.05
    Activations Density 0.017%

    No Known Activations