© 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. 57452
    Prev
    Next
    INDEX
    Explanations

    terms related to data acquisition and system configurations

    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
    allen
    -0.06
    aggi
    -0.06
    اخ
    -0.06
    onth
    -0.06
    ohn
    -0.06
    ãĥĥãĥĦ
    -0.06
    aux
    -0.06
    uran
    -0.06
    ιά
    -0.05
     hearing
    -0.05
    POSITIVE LOGITS
    SCII
    0.09
    ãĥĮ
    0.07
    ewan
    0.07
    elik
    0.07
    chner
    0.07
     kullanarak
    0.07
     alıp
    0.07
    bell
    0.07
    ãĤĴ使
    0.06
     usage
    0.06
    Activations Density 0.032%

    No Known Activations