© 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. 29244
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to air conditioning systems

    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
    ãĤ¢ãĥ¼
    -0.07
    reesome
    -0.07
    ussian
    -0.06
     taper
    -0.06
    akit
    -0.06
    Injector
    -0.06
     resent
    -0.06
    odge
    -0.06
    allocator
    -0.06
     Jud
    -0.06
    POSITIVE LOGITS
     **)&
    0.07
    imals
    0.07
    elta
    0.07
    auses
    0.07
    ارة
    0.07
    addock
    0.06
    mia
    0.06
    cidade
    0.06
    &R
    0.06
    PELL
    0.06
    Activations Density 0.006%

    No Known Activations