© 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. 37771
    Prev
    Next
    INDEX
    Explanations

    is

    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
    _world
    -0.08
     Phelps
    -0.08
     adds
    -0.08
     Hits
    -0.08
    ',)↵
    -0.07
    Hey
    -0.07
     borders
    -0.07
     Desktop
    -0.07
    oner
    -0.07
    qr
    -0.07
    POSITIVE LOGITS
    υπ
    0.08
    lparr
    0.07
     な
    0.07
    -в
    0.07
     Υπο
    0.06
     spos
    0.06
    をした
    0.06
    行为
    0.06
     yapmak
    0.06
    ubits
    0.06
    Activations Density 0.055%

    No Known Activations