© 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. 105343
    Prev
    Next
    INDEX
    Explanations

    technical terms and features related to automotive performance

    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
    ephir
    -0.07
    ream
    -0.06
     Licensing
    -0.06
    LETTE
    -0.06
    ownt
    -0.06
    gren
    -0.06
     dreaming
    -0.06
    eri
    -0.06
    yyyyMMdd
    -0.06
    orris
    -0.06
    POSITIVE LOGITS
    tridge
    0.07
     optim
    0.07
     settings
    0.07
     Profiles
    0.07
    Via
    0.07
    alth
    0.07
    .MixedReality
    0.07
     menus
    0.07
     sill
    0.06
     Adaptive
    0.06
    Activations Density 0.011%

    No Known Activations