© 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. 76568
    Prev
    Next
    INDEX
    Explanations

    elements related to coding and programming functions

    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
    ãĥ³ãĤ¹
    -0.07
     Vác
    -0.07
    rox
    -0.06
    piler
    -0.06
    enti
    -0.06
    üf
    -0.06
    Colorado
    -0.06
    NCY
    -0.06
     tiener
    -0.06
    TimeInterval
    -0.06
    POSITIVE LOGITS
    Liverpool
    0.09
     Liverpool
    0.09
     Liver
    0.08
     hep
    0.08
    Liver
    0.07
     lipstick
    0.07
     Memphis
    0.07
    _suite
    0.07
     Gim
    0.07
    uth
    0.07
    Activations Density 0.010%

    No Known Activations