© 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. 120967
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and references to class definitions and methods

    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
    tuk
    -0.10
    ousse
    -0.07
    sten
    -0.07
    ãn
    -0.07
    shima
    -0.07
    egend
    -0.07
    mia
    -0.07
    reeNode
    -0.06
    .annotation
    -0.06
    Collapse
    -0.06
    POSITIVE LOGITS
     engine
    0.07
     manager
    0.07
    æ»
    0.06
    asi
    0.06
     service
    0.06
     célib
    0.06
    rens
    0.06
     engines
    0.06
     operations
    0.06
    impl
    0.06
    Activations Density 0.087%

    No Known Activations