© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 56313
    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
    ær
    -0.08
    lide
    -0.07
    æ¡Ī
    -0.07
    agua
    -0.07
    ầu
    -0.06
     بÙĪابة
    -0.06
    овеÑĢ
    -0.06
    929
    -0.06
    ãĥ¼ãĥ«
    -0.06
    .getJSONArray
    -0.06
    POSITIVE LOGITS
    ondo
    0.06
     giao
    0.06
    PKG
    0.06
    EFA
    0.06
    itional
    0.06
    .bl
    0.06
    Brief
    0.06
     bl
    0.06
     Moder
    0.06
    Svc
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.