© 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 EvalsExportsAPI 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. 126659
    Prev
    Next
    INDEX
    Explanations

    mentions of future developments and community infrastructure plans

    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
     cán
    -0.07
    baÅŁ
    -0.07
    isko
    -0.07
    æĿī
    -0.07
    caffold
    -0.07
    æ¼
    -0.07
    åįĪ
    -0.07
    lej
    -0.07
    letcher
    -0.07
    .directive
    -0.07
    POSITIVE LOGITS
     public
    0.07
    olis
    0.07
     pods
    0.07
     families
    0.06
    onas
    0.06
     pod
    0.06
     community
    0.06
     Families
    0.06
     supporting
    0.06
     shopping
    0.06
    Activations Density 0.018%

    No Known Activations