© 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. 69651
    Prev
    Next
    INDEX
    Explanations

    terms related to corrections and contributions in theoretical physics equations

    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
     crisp
    -0.06
     Maher
    -0.06
    ctl
    -0.06
     sequel
    -0.06
    /application
    -0.06
     limitations
    -0.05
     Cour
    -0.05
     Aura
    -0.05
    .
    -0.05
     or
    -0.05
    POSITIVE LOGITS
     contribution
    0.10
     contributions
    0.10
     Contribution
    0.09
    _contrib
    0.08
    ÅĽcie
    0.07
    aktiv
    0.07
     canceled
    0.07
     Contributions
    0.07
    contrib
    0.07
    rikes
    0.07
    Activations Density 0.077%

    No Known Activations