© 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. 72759
    Prev
    Next
    INDEX
    Explanations

    various time-related 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
    bbe
    -0.07
    á»īnh
    -0.06
     whim
    -0.06
    úc
    -0.06
    orest
    -0.06
    Ỽt
    -0.06
    UDA
    -0.06
    asto
    -0.06
    cke
    -0.06
    burg
    -0.06
    POSITIVE LOGITS
    /vnd
    0.07
    alled
    0.07
    _registro
    0.06
    Wunused
    0.06
    лÑıв
    0.06
    switch
    0.06
    YO
    0.06
    yo
    0.06
    ALLED
    0.06
    /autoload
    0.06
    Activations Density 0.001%

    No Known Activations