© 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. 120064
    Prev
    Next
    INDEX
    Explanations

    references to grants and funding sources for various programs

    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
    asel
    -0.07
     Holding
    -0.07
    isko
    -0.06
    .study
    -0.06
    ave
    -0.06
    celik
    -0.06
    adar
    -0.06
    isha
    -0.05
    jet
    -0.05
    ibs
    -0.05
    POSITIVE LOGITS
    ë¡Ŀ
    0.07
    ëł
    0.07
     Gallagher
    0.06
    ------+------+
    0.06
    buckets
    0.06
     ФедеÑĢалÑĮ
    0.06
    ucher
    0.06
    SHIP
    0.06
    emey
    0.06
     HRESULT
    0.06
    Activations Density 0.014%

    No Known Activations