© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 85592
    Prev
    Next
    INDEX
    Explanations

    expressions of personal relationships and interactions

    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
     currently
    -0.08
     today
    -0.08
     potentially
    -0.07
    _today
    -0.07
    ä»Ĭ天
    -0.07
     tomorrow
    -0.06
     possibly
    -0.06
     likely
    -0.06
     aggregation
    -0.06
    ms
    -0.06
    POSITIVE LOGITS
     increasingly
    0.07
    æ¸IJ
    0.07
     whenever
    0.07
    //{{
    0.07
    ÑĢÑĸв
    0.07
     Soon
    0.07
    avid
    0.07
    519
    0.07
     Whenever
    0.06
    ataire
    0.06
    Activations Density 0.010%

    No Known Activations