© 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. 15-LLAMASCOPE-RES-131K
    11. 104268
    Prev
    Next
    INDEX
    Explanations

    scientific terms and references related to biology and virology

    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
    podob
    -0.07
    utsch
    -0.07
    ureau
    -0.07
     Populate
    -0.06
     analogy
    -0.06
    chter
    -0.06
    LICENSE
    -0.06
    ekyll
    -0.06
     Signing
    -0.06
    artner
    -0.06
    POSITIVE LOGITS
     HttpServletResponse
    0.07
    CGColor
    0.06
     컨
    0.06
    ATH
    0.06
    iet
    0.06
    reh
    0.06
    _ev
    0.06
    -thumbnails
    0.06
     %{
    0.06
     smr
    0.06
    Activations Density 0.025%

    No Known Activations