© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57123
    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
    ongyang
    -0.07
    .seed
    -0.06
    uilder
    -0.06
    SessionFactory
    -0.06
     imm
    -0.06
     cul
    -0.06
    κη
    -0.06
    икÑĥ
    -0.06
    áty
    -0.06
     ung
    -0.06
    POSITIVE LOGITS
     赤
    0.07
    THR
    0.06
    estro
    0.06
    innie
    0.06
    CHAT
    0.06
     Ingram
    0.06
     æĻ
    0.06
    ogn
    0.06
    aska
    0.06
    ãĥ¼ãĥª
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.