© 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. 124636
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "stage" and other related terms in performance contexts

    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
    ÑĢой
    -0.07
    culus
    -0.07
    dera
    -0.07
    ektiv
    -0.07
    zell
    -0.07
     önlem
    -0.07
    áº
    -0.07
    ongyang
    -0.06
    udes
    -0.06
     aras
    -0.06
    POSITIVE LOGITS
    /on
    0.07
    nas
    0.07
    357
    0.06
    رد
    0.06
    /table
    0.06
     helm
    0.06
    367
    0.06
    .btnExit
    0.06
    439
    0.06
    ic
    0.06
    Activations Density 0.025%

    No Known Activations