© 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. 61833
    Prev
    Next
    INDEX
    Explanations

    quantities and durations related to time and measurements

    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
    ừ
    -0.06
    jist
    -0.06
     Gust
    -0.06
     evet
    -0.06
     dü
    -0.06
    obel
    -0.06
    295
    -0.06
     disag
    -0.06
    plib
    -0.06
    staw
    -0.06
    POSITIVE LOGITS
    å®Įæķ´
    0.10
     entire
    0.09
     complete
    0.09
     full
    0.08
     کاÙħÙĦ
    0.08
    åħ¸
    0.08
     whole
    0.08
    full
    0.08
    half
    0.07
    COMPLETE
    0.07
    Activations Density 0.084%

    No Known Activations