© 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. 127756
    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
    GENCY
    -0.07
    irror
    -0.06
     updated
    -0.06
    bellion
    -0.06
     confronting
    -0.06
     icing
    -0.06
    trans
    -0.06
     bother
    -0.06
    fulWidget
    -0.06
     recal
    -0.06
    POSITIVE LOGITS
    _DST
    0.07
    27
    0.07
    	register
    0.07
     accordion
    0.06
    shi
    0.06
    erd
    0.06
     глу
    0.06
     Ή
    0.06
     sean
    0.06
     Bahrain
    0.06
    Activations Density 0.001%

    No Known Activations