© 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. 39267
    Prev
    Next
    INDEX
    Explanations

    numerical data or 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
      ↵  ↵
    -0.09
    ãģ¨ãģĵãĤį
    -0.08
      ↵
    -0.07
    aneous
    -0.07
    ons
    -0.07
    abyrinth
    -0.07
    ao
    -0.07
        ↵
    -0.07
    ahn
    -0.07
    ÅĻe
    -0.07
    POSITIVE LOGITS
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.09
    ably
    0.08
    ictim
    0.07
    격
    0.07
    alet
    0.07
    671
    0.07
    ï¸ı
    0.07
    ial
    0.07
    cko
    0.07
    ãĥ¥
    0.06
    Activations Density 0.011%

    No Known Activations