© 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. 127137
    Prev
    Next
    INDEX
    Explanations

    terms related to heating and air conditioning services

    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
    åºŃ
    -0.06
    lett
    -0.06
    itel
    -0.06
    uib
    -0.06
    odash
    -0.06
    åĤ·
    -0.06
     wart
    -0.05
     Ferd
    -0.05
    ضر
    -0.05
    olet
    -0.05
    POSITIVE LOGITS
    emer
    0.09
    uffs
    0.09
    iler
    0.08
    _FLAGS
    0.07
    allen
    0.07
     EXEMPLARY
    0.06
    ewise
    0.06
    zsche
    0.06
     registers
    0.06
     wearable
    0.06
    Activations Density 0.002%

    No Known Activations