© 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 EvalsExportsAPI 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. 71262
    Prev
    Next
    INDEX
    Explanations

    URLs and references to digital content

    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
     ÐĴики
    -0.08
    /documents
    -0.07
    isu
    -0.06
    luv
    -0.06
     colleg
    -0.06
    xAD
    -0.06
     mann
    -0.06
    oval
    -0.06
    ourn
    -0.06
    adam
    -0.06
    POSITIVE LOGITS
    ses
    0.07
    DataStream
    0.07
    ynamo
    0.07
    nya
    0.07
    elda
    0.06
     tiener
    0.06
    asin
    0.06
    ungs
    0.06
    usta
    0.06
    embros
    0.06
    Activations Density 0.001%

    No Known Activations