© 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. 94926
    Prev
    Next
    INDEX
    Explanations

    references to musical artists and their performances

    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
     Assembly
    -0.07
    semblies
    -0.07
     Cellular
    -0.07
    Assembly
    -0.07
     olsun
    -0.07
    ppers
    -0.07
    pire
    -0.07
    à¥įà¤ł
    -0.07
    нож
    -0.07
    *sp
    -0.06
    POSITIVE LOGITS
    ubb
    0.07
    %X
    0.06
    FileType
    0.06
     lẽ
    0.06
    .openConnection
    0.05
    .VideoCapture
    0.05
    Disp
    0.05
     tow
    0.05
    :\/\/
    0.05
    ques
    0.05
    Activations Density 0.001%

    No Known Activations