© 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. 128750
    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
    ç«ľ
    -0.07
    [,]
    -0.06
    arkan
    -0.06
     {?>↵
    -0.06
    ayah
    -0.06
    ongan
    -0.06
    osemite
    -0.06
    aran
    -0.06
    atır
    -0.06
    owers
    -0.05
    POSITIVE LOGITS
    ĥĿ
    0.07
     vlas
    0.07
    holm
    0.07
    ãĤĵãģª
    0.06
    este
    0.06
    -utils
    0.06
     Holl
    0.06
    çĤī
    0.06
    azole
    0.06
     chaud
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.