© 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. 57807
    Prev
    Next
    INDEX
    Explanations

    legal entities and organizations involved in court cases

    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
     versus
    -0.08
     sine
    -0.06
    auc
    -0.06
    idlo
    -0.06
    AFX
    -0.06
    elib
    -0.06
     gegen
    -0.06
    etti
    -0.06
    eti
    -0.06
    eah
    -0.06
    POSITIVE LOGITS
     yyn
    0.07
     odense
    0.06
     NGX
    0.06
    vol
    0.06
    entifier
    0.06
    nonnull
    0.06
    InBackground
    0.06
    udu
    0.06
    Ú©ÙĪر
    0.06
    á»ĭnh
    0.06
    Activations Density 0.019%

    No Known Activations