© 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. 15-LLAMASCOPE-RES-131K
    11. 87480
    Prev
    Next
    INDEX
    Explanations

    references to debugging and diagnostic tools in code

    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
    ocks
    -0.07
    croft
    -0.07
    ãģĺ
    -0.07
    idl
    -0.07
    ODB
    -0.07
    andest
    -0.07
    åĢij
    -0.07
    IID
    -0.07
    oj
    -0.07
    رÛĮاÙĨ
    -0.06
    POSITIVE LOGITS
    ging
    0.10
    gers
    0.09
    ogue
    0.08
    ÙĤات
    0.08
    ulous
    0.07
    gable
    0.07
    gett
    0.07
    ged
    0.07
    ulously
    0.07
    osphere
    0.07
    Activations Density 0.019%

    No Known Activations