© 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. 7-RESID-POST-AA
    11. 93855
    Prev
    Next
    INDEX
    Explanations

    External

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ＼↵
    -0.06
     hã
    -0.06
    |)↵
    -0.06
    (book
    -0.06
    单
    -0.06
    cycle
    -0.06
    draw
    -0.06
    criptors
    -0.06
     Identified
    -0.06
     Ed
    -0.05
    POSITIVE LOGITS
    ंडल
    0.06
     Exodus
    0.06
    ЮЛ
    0.06
     Kerala
    0.06
     inward
    0.06
     dein
    0.06
    Insp
    0.06
     Ski
    0.06
     bao
    0.06
     lac
    0.06
    Activations Density 0.004%

    No Known Activations