© 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. 128789
    Prev
    Next
    INDEX
    Explanations

    the word "since" in various contexts

    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
    ohan
    -0.06
    è´¨
    -0.06
     запаÑģ
    -0.05
    /entities
    -0.05
    er
    -0.05
    enburg
    -0.05
     Duck
    -0.05
    omu
    -0.05
     Fantastic
    -0.05
     Fut
    -0.05
    POSITIVE LOGITS
    pNet
    0.08
     Äijó
    0.07
    imedia
    0.07
    GuidId
    0.07
    å¼¥
    0.07
    icker
    0.07
    ÏĦÏħ
    0.07
     subsequently
    0.07
    DataExchange
    0.07
    Å¡ak
    0.07
    Activations Density 0.004%

    No Known Activations