© 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 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. 16395
    Prev
    Next
    INDEX
    Explanations

    references to books and significant concepts in philosophical discussions

    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
     Bowman
    -0.08
     Bowen
    -0.07
     contexts
    -0.07
    ame
    -0.07
    icap
    -0.06
     Lans
    -0.06
    ues
    -0.06
    rome
    -0.06
     context
    -0.06
    etheus
    -0.06
    POSITIVE LOGITS
    chter
    0.07
    eldon
    0.07
    amines
    0.07
    gne
    0.07
    BSD
    0.07
    caf
    0.07
    ẫ
    0.07
    /npm
    0.06
    ìĭľìĺ¤
    0.06
    dens
    0.06
    Activations Density 0.041%

    No Known Activations