© 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. 17-LLAMASCOPE-RES-131K
    11. 89140
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical proofs and theorems

    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
    ooth
    -0.06
    ignet
    -0.06
    uchs
    -0.06
    osh
    -0.06
    ockey
    -0.06
     sobie
    -0.06
    .Model
    -0.06
    ockets
    -0.06
    etu
    -0.05
    ort
    -0.05
    POSITIVE LOGITS
    /max
    0.08
     authDomain
    0.08
    layui
    0.07
    ataires
    0.07
     minimum
    0.07
    :min
    0.07
    minimum
    0.07
     Minimum
    0.07
    avian
    0.07
    max
    0.07
    Activations Density 0.151%

    No Known Activations