© 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 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. 17-LLAMASCOPE-RES-131K
    11. 56070
    Prev
    Next
    INDEX
    Explanations

    phrases related to the maintenance of systems or structures

    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
    quier
    -0.06
    å±
    -0.06
    _ATTRIB
    -0.06
    outu
    -0.06
    ierre
    -0.06
    ermal
    -0.06
    otal
    -0.06
     legit
    -0.06
    ÙĩÙĨ
    -0.06
    .reload
    -0.06
    POSITIVE LOGITS
     infrastructure
    0.08
     instruments
    0.07
     maintained
    0.07
    rab
    0.07
     equipment
    0.07
    curity
    0.07
     Já
    0.07
     Instruments
    0.07
     Zucker
    0.07
     Maint
    0.07
    Activations Density 0.023%

    No Known Activations