© 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 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. 7-RESID-POST-AA
    11. 42719
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
     Tobacco
    -0.07
    桌
    -0.06
     ankle
    -0.06
    Scaled
    -0.06
    (queue
    -0.06
    ijkstra
    -0.06
     Avust
    -0.06
     ah
    -0.06
    (Notification
    -0.06
    กรม
    -0.06
    POSITIVE LOGITS
    лены
    0.07
    ování
    0.06
     Vulner
    0.06
     consideration
    0.06
    ,string
    0.06
     testimon
    0.06
    classification
    0.06
     Accuracy
    0.06
    |(↵
    0.06
     loại
    0.06
    Activations Density 0.138%

    No Known Activations