© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 69384
    Prev
    Next
    INDEX
    Explanations

    terms related to optimization and constraints in 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
    agg
    -0.07
     vic
    -0.07
     favorites
    -0.07
     favourites
    -0.06
     dir
    -0.06
     flagship
    -0.06
    sut
    -0.06
    593
    -0.06
     favourite
    -0.06
     sever
    -0.06
    POSITIVE LOGITS
     among
    0.10
    among
    0.09
     ÑģÑĢеди
    0.09
     amongst
    0.09
     Among
    0.08
    Among
    0.07
    ê°Ĵ
    0.07
    Tick
    0.07
     value
    0.06
    ottie
    0.06
    Activations Density 0.054%

    No Known Activations