© 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. 59717
    Prev
    Next
    INDEX
    Explanations

    references to regional entities and organizations

    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
    coni
    -0.07
    eln
    -0.07
    elo
    -0.07
    ights
    -0.07
    elen
    -0.07
    lico
    -0.06
     éĿ
    -0.06
    ındır
    -0.06
    erman
    -0.06
     æģ
    -0.06
    POSITIVE LOGITS
    ized
    0.08
    izada
    0.07
    ization
    0.07
    icros
    0.07
    mente
    0.07
    .wx
    0.06
    etroit
    0.06
    ize
    0.06
    ongan
    0.06
    dehyde
    0.06
    Activations Density 0.008%

    No Known Activations