© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18488
    Prev
    Next
    INDEX
    Explanations

    terms related to weak solutions in mathematical 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
    .scalablytyped
    -0.08
    abr
    -0.08
    elik
    -0.07
    ÐĴÐŀ
    -0.07
    UTTON
    -0.07
    leness
    -0.07
    رÛĮز
    -0.07
    á»ĵng
    -0.07
    меÑĩ
    -0.07
    墨
    -0.07
    POSITIVE LOGITS
    edly
    0.07
    ingly
    0.06
    uppen
    0.06
     Aqu
    0.06
    otten
    0.06
     Hemp
    0.06
    OSC
    0.06
    resco
    0.06
    opal
    0.05
    ly
    0.05
    Activations Density 0.091%

    No Known Activations