© 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. 30499
    Prev
    Next
    INDEX
    Explanations

    code-related operations that involve adding or modifying components in a user interface

    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
    rana
    -0.07
    mdl
    -0.06
    inka
    -0.06
    DEX
    -0.06
    unnel
    -0.06
    lig
    -0.06
    otre
    -0.06
    ovna
    -0.06
    AndPassword
    -0.06
    ropp
    -0.06
    POSITIVE LOGITS
     WithEvents
    0.07
     anon
    0.07
     addCriterion
    0.07
    umor
    0.07
    nage
    0.06
     ná»iji
    0.06
    InParameter
    0.06
    ót
    0.06
     Advantage
    0.06
    ův
    0.06
    Activations Density 0.001%

    No Known Activations