© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 127381
    Prev
    Next
    INDEX
    Explanations

    phrases that quantify or specify proportions of items 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
    icken
    -0.08
    mdir
    -0.07
    shal
    -0.07
    оÑģÑĥд
    -0.07
    zl
    -0.07
    muz
    -0.07
     ÙģاÙĦ
    -0.07
     fisse
    -0.07
    uled
    -0.07
    conti
    -0.06
    POSITIVE LOGITS
    /all
    0.06
    onal
    0.06
     Portions
    0.06
    aight
    0.06
     portion
    0.06
    ¡
    0.05
     portions
    0.05
     shar
    0.05
    PERT
    0.05
    etsy
    0.05
    Activations Density 0.038%

    No Known Activations