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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84324
    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
    OTO
    -0.07
    ä¸ĬäºĨ
    -0.06
    onom
    -0.06
    oto
    -0.06
    ook
    -0.06
    Become
    -0.06
     sca
    -0.06
    stitial
    -0.05
     Shepherd
    -0.05
     açısından
    -0.05
    POSITIVE LOGITS
    ipse
    0.07
    ependency
    0.07
    enance
    0.06
    prov
    0.06
    .DataVisualization
    0.06
    Å©
    0.06
    _highlight
    0.06
    .executor
    0.06
     пÑĢоÑĦеÑģÑģионалÑĮ
    0.06
    ForResult
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.