© 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. 27964
    Prev
    Next
    INDEX
    Explanations

    tabular data or structures, particularly involving compatibility and values

    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
    getCode
    -0.07
     Dan
    -0.06
     ladder
    -0.06
     Chapel
    -0.06
    ether
    -0.06
    κÏĮ
    -0.06
    isson
    -0.06
    ικο
    -0.06
    Dan
    -0.06
    XmlElement
    -0.06
    POSITIVE LOGITS
    /csv
    0.11
     CSV
    0.10
     csv
    0.10
    csv
    0.10
    (csv
    0.09
    .csv
    0.09
    _csv
    0.08
     columns
    0.08
     line
    0.08
    CSV
    0.08
    Activations Density 0.020%

    No Known Activations