© 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. 106614
    Prev
    Next
    INDEX
    Explanations

    possessive forms of the word "is."

    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
    qv
    -0.07
     Samuel
    -0.07
    ets
    -0.07
    eries
    -0.07
    dál
    -0.07
    453
    -0.06
    ETS
    -0.06
     voks
    -0.06
    ej
    -0.06
    alyzer
    -0.06
    POSITIVE LOGITS
     Legacy
    0.06
     Place
    0.06
    onth
    0.06
    esson
    0.06
     adventures
    0.06
    rig
    0.06
    ë
    0.06
    书记
    0.06
    agues
    0.06
    valuator
    0.06
    Activations Density 0.014%

    No Known Activations