© 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. 54752
    Prev
    Next
    INDEX
    Explanations

    phrases related to consideration or decision-making

    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
    Ìĥ
    -0.07
    dest
    -0.06
    stÅĻÃŃ
    -0.06
    átis
    -0.06
    jal
    -0.06
    ÙĪØ·
    -0.06
    Äħż
    -0.06
    _Tis
    -0.06
    egas
    -0.06
     Anast
    -0.06
    POSITIVE LOGITS
    zell
    0.07
     or
    0.07
     purchase
    0.07
    æĪĸèĢħ
    0.07
    criptor
    0.06
     nového
    0.06
     ÛĮا
    0.06
    748
    0.06
    DLL
    0.06
     upcoming
    0.06
    Activations Density 0.018%

    No Known Activations