© 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. 107845
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements that are likely related to product specifications or performance metrics

    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
    jspx
    -0.08
    $MESS
    -0.08
    using
    -0.07
    #
    -0.07
    autoreleasepool
    -0.07
    ÑĢÑĥд
    -0.07
    hdl
    -0.07
    TEGER
    -0.07
     addCriterion
    -0.07
    REDIENT
    -0.07
    POSITIVE LOGITS
     decom
    0.05
     wor
    0.05
     forc
    0.05
     McInt
    0.05
    Impl
    0.05
    isa
    0.05
     Gros
    0.05
    x
    0.05
     quar
    0.05
     queryInterface
    0.05
    Activations Density 0.061%

    No Known Activations