© 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. 11-RESID-POST-AA
    11. 46493
    Prev
    Next
    INDEX
    Explanations

    iterative steps

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     granddaughter
    -0.06
     hlavou
    -0.06
     Iter
    -0.06
     Fraser
    -0.06
     Sampler
    -0.06
    _fault
    -0.06
    :none
    -0.06
     Mang
    -0.06
     IMO
    -0.06
    TECT
    -0.06
    POSITIVE LOGITS
    	Scanner
    0.07
     Outdoor
    0.06
     "["
    0.06
     fortune
    0.06
    Allows
    0.06
    /support
    0.06
     Externí
    0.06
     Il
    0.06
    ="↵
    0.06
     speakers
    0.06
    Activations Density 0.046%

    No Known Activations