© 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. 4968
    Prev
    Next
    INDEX
    Explanations

    terms related to integration and unified 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
    zew
    -0.07
    licative
    -0.07
    ignKey
    -0.06
    ìŁģ
    -0.06
    URLException
    -0.06
     ç¢
    -0.06
    .tie
    -0.06
    intree
    -0.06
    леÑĢ
    -0.06
    üss
    -0.06
    POSITIVE LOGITS
     approach
    0.09
     Approach
    0.08
    wick
    0.07
     approaches
    0.06
    /int
    0.06
    onian
    0.06
    illon
    0.06
    iant
    0.06
     system
    0.06
    aunch
    0.06
    Activations Density 0.015%

    No Known Activations