© 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. 59322
    Prev
    Next
    INDEX
    Explanations

    phrases related to offering assistance or support

    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
    Ãłm
    -0.06
    bst
    -0.06
    mage
    -0.06
    ãģĮãģĦ
    -0.06
    alsa
    -0.06
     Mayer
    -0.06
    RectTransform
    -0.06
    алов
    -0.06
    ino
    -0.06
    eda
    -0.06
    POSITIVE LOGITS
     you
    0.10
    ä½ł
    0.07
    you
    0.07
    toMatch
    0.07
     your
    0.07
     us
    0.06
     dém
    0.06
    egasus
    0.06
    ä½łçļĦ
    0.06
     Glad
    0.06
    Activations Density 0.011%

    No Known Activations