© 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. 3559
    Prev
    Next
    INDEX
    Explanations

    terms related to mining, processing, and structural integrity

    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
    agt
    -0.07
    ano
    -0.07
     scand
    -0.07
    py
    -0.06
     tvor
    -0.06
    rag
    -0.06
    udu
    -0.06
    CAD
    -0.06
    emin
    -0.06
    ki
    -0.06
    POSITIVE LOGITS
    ĵ¨
    0.08
     during
    0.07
    длÑı
    0.07
    391
    0.07
    HTTPHeader
    0.07
     situations
    0.07
     eldre
    0.07
     lors
    0.07
     various
    0.06
    åŃĿ
    0.06
    Activations Density 0.075%

    No Known Activations