Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 99398
    Prev
    Next
    INDEX
    Explanations

    medical patients

    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
    /alert
    -0.07
     hated
    -0.07
     вып
    -0.06
    ounc
    -0.06
     upside
    -0.06
    heiten
    -0.06
     Package
    -0.06
    Spring
    -0.06
     크
    -0.06
    шую
    -0.06
    POSITIVE LOGITS
     Harbour
    0.08
     Deniz
    0.07
     <=>
    0.07
     satisfactory
    0.06
     forsk
    0.06
     Іван
    0.06
    deposit
    0.06
    lector
    0.06
    ื้
    0.06
    -vous
    0.06
    Activations Density 0.050%

    No Known Activations