© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 110728
    Prev
    Next
    INDEX
    Explanations

    Scientific research / activation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     และ
    -0.06
    complexType
    -0.06
    _timestamp
    -0.06
    婆
    -0.06
     Nguyễn
    -0.06
     гру
    -0.06
     COR
    -0.06
    continued
    -0.06
    .JsonIgnore
    -0.06
    Squared
    -0.06
    POSITIVE LOGITS
     refund
    0.07
     Vanilla
    0.07
     sprav
    0.07
     verwenden
    0.06
    .Quantity
    0.06
     administrator
    0.06
     administrators
    0.06
    困
    0.06
     Structures
    0.06
     Tul
    0.06
    Activations Density 0.046%

    No Known Activations