© 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. 15-RESID-POST-AA
    11. 90251
    Prev
    Next
    INDEX
    Explanations

    (start

    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
    Arial
    -0.06
     Phát
    -0.06
    chrono
    -0.06
    :event
    -0.06
    xEC
    -0.06
    .STRING
    -0.06
    Subviews
    -0.06
    ewe
    -0.06
    _SINGLE
    -0.06
     Ngân
    -0.06
    POSITIVE LOGITS
     eccentric
    0.06
    -time
    0.06
    itored
    0.06
    ！！
    0.06
     Thick
    0.06
     masked
    0.06
    σή
    0.06
     Picture
    0.06
     amnesty
    0.06
    [left
    0.06
    Activations Density 0.000%

    No Known Activations