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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29778
    Prev
    Next
    INDEX
    Explanations

    terms related to satellite technology and broadband coverage

    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
    252
    -0.06
     inline
    -0.06
     ÑĤеÑĩ
    -0.06
    unger
    -0.06
    ahy
    -0.06
    nik
    -0.06
    904
    -0.06
     onStop
    -0.06
     Meh
    -0.06
    allen
    -0.06
    POSITIVE LOGITS
    sat
    0.08
     sat
    0.07
    ä»°
    0.07
    ergency
    0.07
    -global
    0.07
     global
    0.07
     balloons
    0.07
     balloon
    0.07
    subscription
    0.07
    utor
    0.06
    Activations Density 0.002%

    No Known Activations