© 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. 39009
    Prev
    Next
    INDEX
    Explanations

    RowAtIndexPath

    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
    -прав
    -0.07
    姑
    -0.06
     εγκα
    -0.06
     предпри
    -0.06
    ávky
    -0.06
     kijken
    -0.06
    bedPane
    -0.06
     Clo
    -0.06
    уляр
    -0.06
    rze
    -0.06
    POSITIVE LOGITS
    Google
    0.08
    Tap
    0.08
    	swap
    0.07
     function
    0.07
    Research
    0.07
     keyword
    0.07
    requires
    0.07
    weights
    0.07
    оваться
    0.06
    Dimensions
    0.06
    Activations Density 0.001%

    No Known Activations