© 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. 81544
    Prev
    Next
    INDEX
    Explanations

    terms related to complexity and duality in various 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
     herk
    -0.07
     -:
    -0.07
    OUNCE
    -0.07
    åģ¶
    -0.07
    CLU
    -0.07
     didFinish
    -0.07
    sense
    -0.07
    chet
    -0.07
     cellFor
    -0.07
    .bunifuFlatButton
    -0.07
    POSITIVE LOGITS
     mode
    0.09
     position
    0.09
     Mode
    0.07
     state
    0.07
    position
    0.07
    Mode
    0.07
     Position
    0.07
     flux
    0.07
    ä½į
    0.07
     employ
    0.07
    Activations Density 0.058%

    No Known Activations