© 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. 39304
    Prev
    Next
    INDEX
    Explanations

    phrases related to essential features and characteristics of templates or guidelines

    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
    кÑĥÑĢ
    -0.08
    zos
    -0.08
     krát
    -0.07
     VÅ¡ech
    -0.07
    .mousePosition
    -0.07
    usan
    -0.07
    اÙĬد
    -0.07
    Ế
    -0.07
    NÄ°
    -0.07
    vell
    -0.07
    POSITIVE LOGITS
     an
    0.07
     a
    0.06
     l
    0.06
     ther
    0.06
    »
    0.06
    elijk
    0.06
     pur
    0.06
     Pur
    0.06
     expectedResult
    0.06
    缴
    0.06
    Activations Density 0.020%

    No Known Activations