© 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. 70874
    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
    uss
    -0.07
    erer
    -0.07
    877
    -0.06
    lili
    -0.06
    ker
    -0.06
    лÑĸв
    -0.06
    kel
    -0.06
    ongo
    -0.06
    eer
    -0.06
    819
    -0.05
    POSITIVE LOGITS
     ChÆ°Æ¡ng
    0.08
    oice
    0.08
    oogle
    0.07
    rana
    0.07
    adero
    0.07
    Statics
    0.07
    anlar
    0.07
    oft
    0.07
    ãģ«ãģªãģ£ãģ¦
    0.07
     Bilim
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.