© 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. 86694
    Prev
    Next
    INDEX
    Explanations

    words indicating a high level of quality or excellence

    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
    usc
    -0.07
    pras
    -0.07
    othy
    -0.07
    عÙĬ
    -0.07
    alter
    -0.07
    olon
    -0.07
    agne
    -0.06
     Laur
    -0.06
    anal
    -0.06
    anter
    -0.06
    POSITIVE LOGITS
    iances
    0.06
    nte
    0.06
    Ñı
    0.06
    erb
    0.06
    Indented
    0.06
    身ä¸Ĭ
    0.06
    ÙijÙİ
    0.06
    egra
    0.06
    ernote
    0.06
    ÙijÙIJ
    0.06
    Activations Density 0.018%

    No Known Activations