© 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. 77865
    Prev
    Next
    INDEX
    Explanations

    mentions of various access-related topics, particularly in healthcare and education

    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
    ãģıãĤĮ
    -0.07
    Ä°Z
    -0.07
    ãĥ¬ãĤ¹
    -0.06
    _requirements
    -0.06
    èµ·æĿ¥
    -0.06
    æĪı
    -0.06
    _BOUND
    -0.06
    æł·åŃIJ
    -0.06
    rient
    -0.06
     unto
    -0.06
    POSITIVE LOGITS
     resources
    0.11
    via
    0.09
     via
    0.08
     Resources
    0.08
    resources
    0.07
     sources
    0.07
     инÑĦоÑĢмаÑĨии
    0.07
     través
    0.07
     Esc
    0.07
     OTHERWISE
    0.07
    Activations Density 0.068%

    No Known Activations