© 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. 19-RESID-POST-AA
    11. 126835
    Prev
    Next
    INDEX
    Explanations

    Saying what others want

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    転
    -0.06
     upp
    -0.06
     موب
    -0.06
     dosud
    -0.06
     Maui
    -0.06
    BERT
    -0.06
    퓨터
    -0.06
    imento
    -0.06
    urlpatterns
    -0.06
     treff
    -0.06
    POSITIVE LOGITS
     declined
    0.07
     respondsToSelector
    0.07
    ��
    0.07
    [Double
    0.06
     trays
    0.06
    719
    0.06
     //----------------
    0.06
     Age
    0.06
    Lite
    0.06
    olume
    0.06
    Activations Density 0.153%

    No Known Activations