© 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. 59231
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to optimization and cost efficiency in planning or algorithms

    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
    quia
    -0.07
    enge
    -0.07
    å½ķ
    -0.07
    ndx
    -0.07
    jandro
    -0.07
    Deal
    -0.06
    ieten
    -0.06
    idot
    -0.06
    irut
    -0.06
    ilder
    -0.06
    POSITIVE LOGITS
     optimal
    0.13
     optimum
    0.10
     optim
    0.10
     optimization
    0.10
     strategy
    0.10
     Optimization
    0.09
     Optim
    0.09
     optimize
    0.09
    optim
    0.09
     Opt
    0.09
    Activations Density 0.096%

    No Known Activations