© 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. 72314
    Prev
    Next
    INDEX
    Explanations

    numbers and their context within dates or time references

    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
     May
    -0.07
     Sept
    -0.07
    fal
    -0.07
    f
    -0.06
     June
    -0.06
     September
    -0.06
     July
    -0.06
     contrary
    -0.06
     November
    -0.06
    äºĶæľĪ
    -0.06
    POSITIVE LOGITS
    presso
    0.08
    #
    0.07
    _ioctl
    0.07
    luet
    0.07
     æĻ´
    0.07
    TriState
    0.07
    ãĥ¼ãĥĩ
    0.07
    isoft
    0.07
    phin
    0.07
    terdam
    0.07
    Activations Density 0.038%

    No Known Activations