© 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. 92380
    Prev
    Next
    INDEX
    Explanations

    terms related to optimization and queries in technical contexts

    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
     vám
    -0.07
     NÄĽm
    -0.07
    UpDown
    -0.06
    .isActive
    -0.06
    ully
    -0.06
    ednou
    -0.06
    ίδα
    -0.06
    VOKE
    -0.06
    دÙĬ
    -0.06
     QDateTime
    -0.06
    POSITIVE LOGITS
    yll
    0.07
    aoke
    0.07
    ategory
    0.06
    herits
    0.06
    apor
    0.06
    fy
    0.06
    üzel
    0.06
    deaux
    0.06
    ngrx
    0.06
    .Globalization
    0.06
    Activations Density 0.039%

    No Known Activations