© 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 EvalsExportsinterp-engineNEWAPI 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. 105037
    Prev
    Next
    INDEX
    Explanations

    phrases related to articles and publications

    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
     bibliography
    -0.07
    ay
    -0.06
     ↵
    -0.06
    ｡
    -0.06
     تÙģ
    -0.06
     Fay
    -0.06
    CodeGen
    -0.06
     /*!<
    -0.05
     закÑĥп
    -0.05
     Payne
    -0.05
    POSITIVE LOGITS
    ève
    0.07
    eking
    0.07
     journals
    0.07
     journal
    0.07
    elper
    0.07
    abstract
    0.07
    astro
    0.07
     embargo
    0.07
    npj
    0.07
    ırı
    0.06
    Activations Density 0.007%

    No Known Activations