© 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. 126045
    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
    æĭĵ
    -0.08
    ï¼ł
    -0.07
    swire
    -0.07
    æ³ķ人
    -0.07
    tout
    -0.07
    erchant
    -0.07
    anut
    -0.07
     ÑĤÑı
    -0.07
    寸
    -0.07
    itches
    -0.07
    POSITIVE LOGITS
    vu
    0.07
     Bee
    0.07
     value
    0.06
    oli
    0.06
     Ru
    0.06
     analog
    0.06
     .
    0.06
    bee
    0.06
     Davidson
    0.06
     Vehicles
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.