© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 15964
    Prev
    Next
    INDEX
    Explanations

    key concepts related to supply chain management and its impact on various stakeholders

    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
    ushima
    -0.08
    νι
    -0.07
    UBLISH
    -0.07
    aval
    -0.06
    باش
    -0.06
     à¤Ĩ
    -0.06
    .isNotBlank
    -0.06
    .erb
    -0.06
     Availability
    -0.06
     cherry
    -0.06
    POSITIVE LOGITS
     footh
    0.08
    igest
    0.07
     insight
    0.07
    CESS
    0.07
     rid
    0.06
     respect
    0.06
    ç¨
    0.06
    rieb
    0.06
    traction
    0.06
    uner
    0.06
    Activations Density 0.046%

    No Known Activations