© 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 EvalsExportsinterp-engineNEWAPI 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. 37362
    Prev
    Next
    INDEX
    Explanations

    ://

    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
     Dimensions
    -0.06
    Magn
    -0.06
    ثمان
    -0.06
     CircularProgress
    -0.06
     ind
    -0.06
    cip
    -0.06
    Changing
    -0.06
     prof
    -0.06
     trùng
    -0.06
    ']}'
    -0.06
    POSITIVE LOGITS
    =\'
    0.07
    ตา
    0.07
     colleague
    0.06
    _finalize
    0.06
    asına
    0.06
     disables
    0.06
     supplementary
    0.06
     �
    0.06
    vtk
    0.06
     Kil
    0.06
    Activations Density 0.002%

    No Known Activations