© 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. 28060
    Prev
    Next
    INDEX
    Explanations

    the presence of items or entities related to organization and structure in various 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
    cken
    -0.07
    hled
    -0.06
    PCS
    -0.06
    olls
    -0.06
     pcs
    -0.06
    cone
    -0.06
    _except
    -0.06
    erate
    -0.06
    ÏĦί
    -0.06
    hausen
    -0.06
    POSITIVE LOGITS
     each
    0.19
    each
    0.15
     EACH
    0.15
     Each
    0.14
     кажд
    0.14
     cada
    0.14
    Each
    0.13
     каждого
    0.13
     chaque
    0.13
     кожного
    0.13
    Activations Density 0.215%

    No Known Activations