© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 104291
    Prev
    Next
    INDEX
    Explanations

    technical or metadata terms related to programming and software generation

    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
    meli
    -0.07
    SPORT
    -0.07
    archive
    -0.07
    ynom
    -0.07
    straction
    -0.07
    mse
    -0.07
    виÑĤ
    -0.07
    pNet
    -0.07
    omo
    -0.07
    одо
    -0.06
    POSITIVE LOGITS
    ç«ĭãģ¦
    0.06
    LED
    0.06
     GNU
    0.06
    ITTE
    0.06
    OLE
    0.06
    chap
    0.06
     Salmon
    0.06
    896
    0.06
    ouz
    0.05
    QRS
    0.05
    Activations Density 0.001%

    No Known Activations