© 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. 87961
    Prev
    Next
    INDEX
    Explanations

    concepts related to redundancy and fault tolerance in systems

    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
    ptron
    -0.07
    yas
    -0.07
    OUNDS
    -0.07
    mue
    -0.07
    spm
    -0.07
     seins
    -0.07
    νÏī
    -0.07
    ãĥĮ
    -0.07
     Liberation
    -0.07
    ONSE
    -0.07
    POSITIVE LOGITS
     redundancy
    0.07
     system
    0.07
     fail
    0.07
    backup
    0.07
     physical
    0.06
     backup
    0.06
    icing
    0.06
    meld
    0.06
     paraph
    0.06
    ness
    0.06
    Activations Density 0.008%

    No Known Activations