© 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. 118751
    Prev
    Next
    INDEX
    Explanations

    numerical references and citations in scientific texts

    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
    indi
    -0.07
    wal
    -0.07
    á»±
    -0.06
     fle
    -0.06
    astle
    -0.06
    ÑĢеÑī
    -0.06
    çļĦå£°éŁ³
    -0.06
     Hath
    -0.06
    clus
    -0.06
    ÑĢÑıдÑĥ
    -0.06
    POSITIVE LOGITS
    zeros
    0.07
    ebek
    0.07
     [âĢ¦]↵↵
    0.06
    HECK
    0.06
    gfx
    0.06
    VERIFY
    0.06
    akra
    0.06
     (){
    0.06
    ushman
    0.06
    BuilderFactory
    0.06
    Activations Density 0.011%

    No Known Activations