© 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. 85584
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structure related to web development

    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
     Tus
    -0.06
    elli
    -0.06
    ست
    -0.06
    awi
    -0.06
    ä¿®
    -0.06
     Tel
    -0.06
    936
    -0.05
     waivers
    -0.05
    StateException
    -0.05
    à¸ģ
    -0.05
    POSITIVE LOGITS
    alet
    0.08
    uyết
    0.07
    inqu
    0.07
    aviolet
    0.07
    ãİ
    0.07
     ÙģÙĬÙĩا
    0.07
    éĪ
    0.07
    xAC
    0.07
    HideInInspector
    0.07
    .numberOfLines
    0.07
    Activations Density 0.029%

    No Known Activations