© 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. 17-LLAMASCOPE-RES-131K
    11. 31262
    Prev
    Next
    INDEX
    Explanations

    specific astronomical phenomena and quantifiable data related to cosmic events

    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
     radix
    -0.07
    ideo
    -0.07
    ighting
    -0.06
     clim
    -0.06
     bì
    -0.06
     koÅŁul
    -0.06
    ETCH
    -0.06
    vide
    -0.06
     ÙĦغ
    -0.06
     ÑģоÑĢ
    -0.06
    POSITIVE LOGITS
    agli
    0.07
     measurements
    0.07
     Measurements
    0.07
    illisecond
    0.06
    XS
    0.06
     Sloan
    0.06
     Measurement
    0.06
     measurement
    0.06
    uzz
    0.06
     unusual
    0.06
    Activations Density 0.003%

    No Known Activations