© 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. 126612
    Prev
    Next
    INDEX
    Explanations

    references to official statements or press releases

    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
    inç
    -0.08
    olio
    -0.06
    ailability
    -0.06
     rip
    -0.06
    agini
    -0.06
     plus
    -0.05
     Mail
    -0.05
    ään
    -0.05
     Plus
    -0.05
     mu
    -0.05
    POSITIVE LOGITS
    uku
    0.07
    ucz
    0.07
    ugin
    0.07
     Wilkinson
    0.07
     embargo
    0.07
    istring
    0.07
    º
    0.07
    uml
    0.07
     press
    0.06
    ulta
    0.06
    Activations Density 0.003%

    No Known Activations