© 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. 46564
    Prev
    Next
    INDEX
    Explanations

    1

    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
    illo
    -0.06
    rael
    -0.06
     Gupta
    -0.06
    illos
    -0.06
    ุล
    -0.06
    	cfg
    -0.06
    Γ
    -0.06
     cherished
    -0.06
    ieres
    -0.06
    zM
    -0.05
    POSITIVE LOGITS
     movements
    0.07
    平均
    0.07
    _module
    0.07
    -h
    0.07
    群
    0.07
     الاقتص
    0.06
    -million
    0.06
    чно
    0.06
     عند
    0.06
     diesen
    0.06
    Activations Density 0.020%

    No Known Activations