© 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. 86947
    Prev
    Next
    INDEX
    Explanations

    references to music notation and its interpretation

    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
    legg
    -0.07
     acts
    -0.07
    à¸ĺ
    -0.06
     stores
    -0.06
     esl
    -0.06
    _roi
    -0.06
    ibri
    -0.06
    ãĤµãĤ¤
    -0.06
    /portfolio
    -0.06
    asca
    -0.06
    POSITIVE LOGITS
    zier
    0.08
    ingleton
    0.07
     ferm
    0.07
    rie
    0.07
    éri
    0.06
    resolved
    0.06
    ALES
    0.06
    лен
    0.06
    Breadcrumb
    0.06
     ÑĪп
    0.06
    Activations Density 0.025%

    No Known Activations