© 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. 79983
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and publications

    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
    651
    -0.07
    631
    -0.06
     myster
    -0.06
    orts
    -0.06
    olleyError
    -0.06
    ort
    -0.06
    olare
    -0.06
    740
    -0.06
    nat
    -0.06
    ám
    -0.06
    POSITIVE LOGITS
     Journal
    0.07
     dame
    0.07
    ANJI
    0.06
    apur
    0.06
     journal
    0.06
    mesinin
    0.06
     Dame
    0.06
    eres
    0.06
    ĨĴ
    0.06
    ä¸ĢåĮº
    0.06
    Activations Density 0.013%

    No Known Activations