© 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. 118049
    Prev
    Next
    INDEX
    Explanations

    features related to home heating and cooling 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
     Empty
    -0.06
     Pavel
    -0.06
    jal
    -0.06
    antro
    -0.06
    onga
    -0.06
    endez
    -0.06
     tal
    -0.06
     empty
    -0.06
    asurable
    -0.06
    /filepath
    -0.06
    POSITIVE LOGITS
     system
    0.12
    system
    0.11
    ystem
    0.11
     ÑģиÑģÑĤема
    0.10
    -system
    0.10
    ç³»ç»Ł
    0.09
    .system
    0.09
     sistema
    0.09
     ÑģиÑģÑĤемÑĥ
    0.09
     SYSTEM
    0.08
    Activations Density 0.021%

    No Known Activations