© 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. 80214
    Prev
    Next
    INDEX
    Explanations

    concepts related to economic systems and structures

    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
    adic
    -0.06
    ÑĢей
    -0.06
    rang
    -0.06
    ë²Į
    -0.06
    人æ°ij
    -0.06
    erable
    -0.06
    ney
    -0.06
     shortest
    -0.06
     integrity
    -0.06
     reportedly
    -0.06
    POSITIVE LOGITS
     conseils
    0.06
    reative
    0.06
    owi
    0.06
    èµ·æĿ¥
    0.06
    -Key
    0.06
     relative
    0.06
     partly
    0.06
    orta
    0.06
    å¾Ħ
    0.06
    INGER
    0.06
    Activations Density 0.006%

    No Known Activations