© 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. 69740
    Prev
    Next
    INDEX
    Explanations

    numerical values and terms related to measurements or quantities

    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
     nues
    -0.07
    illes
    -0.07
    é³´
    -0.06
    /raw
    -0.06
    enin
    -0.06
    entin
    -0.06
    ioxide
    -0.06
    enstein
    -0.06
     envelop
    -0.06
    ÑģÑĤанов
    -0.06
    POSITIVE LOGITS
     dozen
    0.09
     sayıda
    0.09
     numerous
    0.08
     number
    0.08
    bagai
    0.08
    -many
    0.08
     aantal
    0.08
     several
    0.08
    DownList
    0.07
    aucoup
    0.07
    Activations Density 0.031%

    No Known Activations