© 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. 81207
    Prev
    Next
    INDEX
    Explanations

    references 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
    etooth
    -0.08
    allen
    -0.07
    cih
    -0.07
    athom
    -0.07
    umpt
    -0.07
    yscale
    -0.07
    bose
    -0.06
    loff
    -0.06
    .scalablytyped
    -0.06
    æŃ¯
    -0.06
    POSITIVE LOGITS
     Satellite
    0.08
     satellite
    0.08
     capacity
    0.07
    CAPE
    0.07
     satellites
    0.07
    sat
    0.07
    jabi
    0.06
    pole
    0.06
     operator
    0.06
     Tin
    0.06
    Activations Density 0.004%

    No Known Activations