© 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. 54199
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting exclusivity or limitation

    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
    BuilderFactory
    -0.07
    apur
    -0.06
    opper
    -0.06
    aign
    -0.06
    itere
    -0.06
    ubar
    -0.06
    DBObject
    -0.06
    ault
    -0.06
    ushima
    -0.06
    /perl
    -0.06
    POSITIVE LOGITS
    imb
    0.06
    .sd
    0.06
    ãĤ¸
    0.06
    lector
    0.06
    itals
    0.06
    ÎŃÏģα
    0.06
    ynchronously
    0.06
     Geh
    0.06
    ohn
    0.06
     Jennings
    0.06
    Activations Density 0.006%

    No Known Activations