© 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. 9-LLAMASCOPE-RES-131K
    11. 98264
    Prev
    Next
    INDEX
    Explanations

    references to technology and telecommunications

    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
     ÑĤи
    -0.08
    /Dk
    -0.08
     Breakfast
    -0.07
    utzer
    -0.07
    serter
    -0.07
    ilim
    -0.07
    ieux
    -0.07
    ROID
    -0.07
    ãĤĥ
    -0.07
    tu
    -0.06
    POSITIVE LOGITS
    ilm
    0.06
     Schro
    0.06
     compatible
    0.06
    eron
    0.06
     rejected
    0.06
     reject
    0.05
     compatibility
    0.05
    erken
    0.05
     rejection
    0.05
     Coron
    0.05
    Activations Density 0.004%

    No Known Activations