© 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. 15-LLAMASCOPE-RES-131K
    11. 88827
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" and its meanings in various contexts

    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
    ÛĮØ´Ùĩ
    -0.07
    ough
    -0.07
    ówn
    -0.07
    æĤ
    -0.07
    iele
    -0.07
    oug
    -0.07
    Scalars
    -0.06
    portlet
    -0.06
    ignite
    -0.06
    adia
    -0.06
    POSITIVE LOGITS
     warrant
    0.07
    xo
    0.06
    nil
    0.06
    rup
    0.06
    ores
    0.06
    dy
    0.06
    orem
    0.06
    ãĥªãĥ¼ãĤº
    0.06
    ctype
    0.05
    isks
    0.05
    Activations Density 0.007%

    No Known Activations