© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 119803
    Prev
    Next
    INDEX
    Explanations

    references to studies, research, and analyses related to health and policy impacts

    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
    ë°
    -0.06
    -
    -0.05
     sometimes
    -0.05
     sais
    -0.05
    eder
    -0.05
    agem
    -0.05
     fairly
    -0.05
     famously
    -0.05
     usually
    -0.05
    kowski
    -0.05
    POSITIVE LOGITS
     similarly
    0.09
    ìłł
    0.08
    etim
    0.08
     now
    0.08
     thêm
    0.07
    URRENT
    0.07
     ebenfalls
    0.07
    .scalablytyped
    0.07
     agora
    0.07
    ÑģиÑĤ
    0.07
    Activations Density 0.026%

    No Known Activations