© 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. 108374
    Prev
    Next
    INDEX
    Explanations

    references to patent applications and their details

    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
    ÑĤап
    -0.07
    idak
    -0.07
    lio
    -0.07
    ellar
    -0.07
    å¹ķ
    -0.07
    á»Ń
    -0.06
     operational
    -0.06
    loor
    -0.06
    iffin
    -0.06
    urette
    -0.06
    POSITIVE LOGITS
     patent
    0.08
    èįī
    0.07
    Pat
    0.07
     Invent
    0.07
     patents
    0.07
     Euras
    0.06
     invention
    0.06
     Patent
    0.06
     abstract
    0.06
     Pat
    0.06
    Activations Density 0.062%

    No Known Activations