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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95975
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istrovstvÃŃ
    -0.07
    inia
    -0.07
    019
    -0.06
    awan
    -0.06
    ç¾
    -0.06
    aimassage
    -0.06
    igner
    -0.06
    inne
    -0.06
    imestep
    -0.06
    .apply
    -0.06
    POSITIVE LOGITS
    inspace
    0.07
    Ui
    0.06
     اب
    0.06
    usal
    0.06
    -svg
    0.06
    ClientRect
    0.06
    arkin
    0.06
     æĺŁ
    0.06
    inte
    0.06
    urg
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.