© 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. 72889
    Prev
    Next
    INDEX
    Explanations

    denote

    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
    Generic
    -0.07
    270
    -0.07
     CONVERT
    -0.06
     magma
    -0.06
    ег
    -0.06
     emphasis
    -0.06
    markup
    -0.06
    $max
    -0.06
    unused
    -0.06
    ैं।
    -0.06
    POSITIVE LOGITS
    -pointer
    0.07
    tiv
    0.07
     видов
    0.07
     Abbas
    0.07
    DK
    0.06
     Naz
    0.06
     Khi
    0.06
     FEC
    0.06
    saida
    0.06
    :"",
    0.06
    Activations Density 0.010%

    No Known Activations