© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98037
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and equations related to physics or scientific notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    annon
    -0.07
    enor
    -0.07
    823
    -0.07
    ãĥ¼ãĤ¿
    -0.06
    tah
    -0.06
    .ASCII
    -0.06
    iazza
    -0.06
    LEC
    -0.06
     Zus
    -0.06
    952
    -0.06
    POSITIVE LOGITS
    à¸ģำ
    0.06
    WARE
    0.06
    MAND
    0.06
    pray
    0.06
    ½
    0.06
    ãĥ³ãĥĸ
    0.06
    onya
    0.06
    anton
    0.06
    FXML
    0.06
     Backend
    0.05
    Activations Density 0.254%

    No Known Activations