© 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 EvalsExportsinterp-engineNEWAPI 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. 92600
    Prev
    Next
    INDEX
    Explanations

    concepts related to low-loss energy systems and environmental considerations in technology and infrastructure

    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
    ikel
    -0.07
    ÑħÑĥ
    -0.07
    oret
    -0.07
    aise
    -0.07
    _unicode
    -0.07
    jak
    -0.07
    antan
    -0.07
    ipse
    -0.07
    èģ
    -0.07
    ÑĮ
    -0.06
    POSITIVE LOGITS
     need
    0.12
    need
    0.10
     requirement
    0.09
     needs
    0.09
     want
    0.08
     ÑĤÑĢебÑĥеÑĤÑģÑı
    0.08
     besoin
    0.08
     Need
    0.08
     cần
    0.08
    Need
    0.08
    Activations Density 0.038%

    No Known Activations