© 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. 41897
    Prev
    Next
    INDEX
    Explanations

    references to time durations and intervals

    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
    ожд
    -0.07
    ̧
    -0.07
    -spacing
    -0.06
    amet
    -0.06
    dued
    -0.06
    awl
    -0.06
     prec
    -0.06
    mony
    -0.06
    rita
    -0.06
    ds
    -0.06
    POSITIVE LOGITS
    ãģŁãģı
    0.09
     late
    0.07
    ingo
    0.07
     period
    0.07
     beginning
    0.07
     starting
    0.07
     ending
    0.07
    irket
    0.06
    illing
    0.06
    æľ«
    0.06
    Activations Density 0.018%

    No Known Activations