© 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. 46968
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and fragments

    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
     Managers
    -0.07
     forging
    -0.06
    Friends
    -0.06
    ptr
    -0.06
    企業
    -0.06
     eating
    -0.06
    (Web
    -0.06
    _WR
    -0.06
     collaborated
    -0.06
     Hoch
    -0.06
    POSITIVE LOGITS
    になる
    0.07
     گرفت
    0.06
    _dependencies
    0.06
     UserProfile
    0.06
     INCLUDED
    0.06
    ToPoint
    0.06
     moving
    0.06
    get
    0.06
    apsed
    0.06
    (Error
    0.06
    Activations Density 0.036%

    No Known Activations