© 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. 70238
    Prev
    Next
    INDEX
    Explanations

    numeric values and mathematical operations within code

    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
    orum
    -0.07
    on
    -0.06
     Musk
    -0.06
     -*-č↵
    -0.06
    ig
    -0.06
    ip
    -0.06
     bubbles
    -0.06
    ãĢģ
    -0.06
     пÑĢип
    -0.06
     Centers
    -0.06
    POSITIVE LOGITS
     etc
    0.09
    etc
    0.09
     hepsi
    0.08
     respectively
    0.07
     altogether
    0.07
    achsen
    0.07
     모ëijIJ
    0.07
     DropIndex
    0.07
    respect
    0.07
    herits
    0.07
    Activations Density 0.055%

    No Known Activations