© 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. 28345
    Prev
    Next
    INDEX
    Explanations

    phrases related to convenience and service offerings

    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
    ä¸įå¾Ĺ
    -0.06
    ÃŃa
    -0.06
    [
    -0.06
     fuck
    -0.06
    inder
    -0.06
    θεν
    -0.06
    cent
    -0.06
    ogs
    -0.06
     instance
    -0.06
    Span
    -0.05
    POSITIVE LOGITS
    _hooks
    0.07
     BÄ°L
    0.07
    ==>
    0.07
    inton
    0.07
     anymore
    0.07
    ìĦ¸ìļĶ
    0.07
    _ctxt
    0.07
     ÑģÑĮогоднÑĸ
    0.07
    vu
    0.07
    amarin
    0.06
    Activations Density 0.017%

    No Known Activations