© 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. 71215
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical applications and definitions in specific 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
     amen
    -0.07
     Tide
    -0.06
    amen
    -0.06
    kul
    -0.06
     Amen
    -0.06
    Multiplicity
    -0.06
    quia
    -0.06
     Ob
    -0.06
    _mC
    -0.06
     responsibility
    -0.05
    POSITIVE LOGITS
    udit
    0.07
    oji
    0.07
    ukkan
    0.07
    cases
    0.07
    uggy
    0.07
    óng
    0.07
    ENCHMARK
    0.07
    eken
    0.07
    ichten
    0.07
    elson
    0.06
    Activations Density 0.085%

    No Known Activations