© 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. 117007
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and acknowledgment

    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
    toa
    -0.08
     erfahren
    -0.06
    Gear
    -0.06
    à¥įमà¤ķ
    -0.06
     selber
    -0.06
    erd
    -0.06
    lahoma
    -0.06
    殿
    -0.06
    vest
    -0.06
    hus
    -0.06
    POSITIVE LOGITS
     for
    0.08
     за
    0.07
    สำหร
    0.07
     için
    0.07
     AUTHORS
    0.07
     CONTRIBUTORS
    0.07
    for
    0.07
    osen
    0.06
     whoever
    0.06
    StateChanged
    0.06
    Activations Density 0.007%

    No Known Activations