© 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. 15-RESID-POST-AA
    11. 4096
    Prev
    Next
    INDEX
    Explanations

    //

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     opak
    -0.07
     共
    -0.07
     gerektir
    -0.07
     bpm
    -0.06
     transitions
    -0.06
    -transition
    -0.06
     identities
    -0.06
    TRS
    -0.06
    dyn
    -0.06
    -parts
    -0.06
    POSITIVE LOGITS
     ex
    0.07
     Иванов
    0.07
    _initialize
    0.07
     треть
    0.07
    ा:
    0.06
    لیت
    0.06
     nevy
    0.06
     solar
    0.06
     серьез
    0.06
    _APPS
    0.06
    Activations Density 0.003%

    No Known Activations