© 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. 130380
    Prev
    Next
    INDEX
    Explanations

    numerical representations or lists, typically in the format of options or steps in a process

    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
    oor
    -0.07
    asca
    -0.07
    .unbind
    -0.07
     banc
    -0.06
    vol
    -0.06
    #
    -0.06
    âĢ¦)↵↵
    -0.06
     Hava
    -0.06
    Ŀì²´
    -0.06
    -FIRST
    -0.06
    POSITIVE LOGITS
     transit
    0.06
    iken
    0.06
    inka
    0.06
    ekyll
    0.06
     Licensed
    0.06
     GUI
    0.06
     Holl
    0.06
    eding
    0.05
    isse
    0.05
     both
    0.05
    Activations Density 0.015%

    No Known Activations