© 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. 11-RESID-POST-AA
    11. 36987
    Prev
    Next
    INDEX
    Explanations

    wisdom

    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
     ubyt
    -0.07
     металли
    -0.07
     elt
    -0.07
    <label
    -0.06
     pictures
    -0.06
     招
    -0.06
     свид
    -0.06
     صفحه
    -0.06
     عملیات
    -0.06
     хлоп
    -0.06
    POSITIVE LOGITS
     wisdom
    0.15
     Wisdom
    0.13
     wise
    0.09
     wisely
    0.08
    conomics
    0.08
     Wise
    0.08
    .dom
    0.07
    Wis
    0.07
     Vis
    0.07
     Wis
    0.07
    Activations Density 0.009%

    No Known Activations