© 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. 3666
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "constant" or stability

    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
    rapy
    -0.07
    SError
    -0.07
    ornado
    -0.07
    /std
    -0.07
    iron
    -0.06
    idle
    -0.06
    rypt
    -0.06
    iffer
    -0.06
    kou
    -0.06
    ivot
    -0.06
    POSITIVE LOGITS
    ley
    0.07
    \Bundle
    0.06
     ActionTypes
    0.06
    leigh
    0.06
    aga
    0.06
    riel
    0.06
    cba
    0.06
    nock
    0.06
     Cyril
    0.06
    inden
    0.06
    Activations Density 0.003%

    No Known Activations