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. 7-RESID-POST-AA
    6. 75382
    Prev
    Next
    INDEX
    Explanations

    window

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     militia
    -0.07
     Minute
    -0.07
     Courses
    -0.07
    .re
    -0.07
     courte
    -0.07
     Aynı
    -0.06
     Bru
    -0.06
     любов
    -0.06
    ضم
    -0.06
     memnun
    -0.06
    POSITIVE LOGITS
     window
    0.09
     Window
    0.09
     windows
    0.08
    window
    0.08
     WINDOW
    0.07
    =",
    0.07
     makes
    0.06
    WINDOW
    0.06
    landscape
    0.06
    <>↵
    0.06
    Activations Density 0.006%

    No Known Activations