© 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. 62179
    Prev
    Next
    INDEX
    Explanations

    references to classical and quantum physics concepts, particularly regarding solutions and methods

    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
    .DefaultCellStyle
    -0.08
    ικ
    -0.08
    êu
    -0.07
    clause
    -0.07
    orra
    -0.07
    lli
    -0.07
    koli
    -0.07
    typeid
    -0.07
    kus
    -0.07
    _statuses
    -0.07
    POSITIVE LOGITS
    ity
    0.07
    ly
    0.07
     Shannon
    0.07
     counterpart
    0.07
    LOC
    0.06
    avel
    0.06
    im
    0.06
     Bened
    0.06
    erin
    0.06
    ization
    0.06
    Activations Density 0.008%

    No Known Activations