© 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. 92577
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to various academic subjects

    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
    %C
    -0.09
     submodule
    -0.07
    styleType
    -0.06
    agement
    -0.06
    енз
    -0.06
    adin
    -0.06
    /*č↵
    -0.06
    ÑĤаж
    -0.06
    /or
    -0.06
    undry
    -0.06
    POSITIVE LOGITS
    anio
    0.07
    ẹ
    0.07
     systems
    0.07
    üb
    0.07
    neh
    0.06
     ones
    0.06
    educt
    0.06
     firms
    0.06
    Blob
    0.06
     programs
    0.06
    Activations Density 0.043%

    No Known Activations