© 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. 77210
    Prev
    Next
    INDEX
    Explanations

    key concepts and terminology related to mechanisms and methodologies in analytical discussions

    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
    uckle
    -0.09
    oice
    -0.06
    adem
    -0.06
    aggio
    -0.06
     par
    -0.06
     ISSN
    -0.06
     ÑĩеÑĢ
    -0.06
    ico
    -0.06
    .getService
    -0.06
    iren
    -0.06
    POSITIVE LOGITS
     altogether
    0.19
     than
    0.18
    than
    0.15
     THAN
    0.15
    _than
    0.14
    -than
    0.13
     Than
    0.13
    Than
    0.13
     entirely
    0.12
     než
    0.12
    Activations Density 0.036%

    No Known Activations