© 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. 15-LLAMASCOPE-RES-131K
    11. 27353
    Prev
    Next
    INDEX
    Explanations

    terms related to the culinary and medicinal uses of plants

    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
    Nie
    -0.07
    edin
    -0.07
    heimer
    -0.07
     Nie
    -0.07
    ftime
    -0.06
    nex
    -0.06
    Ùģت
    -0.06
    idle
    -0.06
    eki
    -0.06
    Ticket
    -0.06
    POSITIVE LOGITS
    ãĥ¬ãĥ³
    0.07
    _INCLUDE
    0.06
    afi
    0.06
    ORIZ
    0.06
     ve
    0.06
    ATAR
    0.06
    Mic
    0.06
     Blanch
    0.06
    mav
    0.05
     Sink
    0.05
    Activations Density 0.013%

    No Known Activations