© 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. 29165
    Prev
    Next
    INDEX
    Explanations

    elements related to software configuration and data handling processes

    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
    ãĥ³ãĥķ
    -0.07
     @$_
    -0.07
    istros
    -0.06
    uppy
    -0.06
    assen
    -0.05
    verige
    -0.05
     blinking
    -0.05
    UDGE
    -0.05
    akter
    -0.05
    InputElement
    -0.05
    POSITIVE LOGITS
    लब
    0.08
    ror
    0.08
    urma
    0.07
    ॰
    0.07
    ucene
    0.07
    (AT
    0.06
    _GPU
    0.06
    .CG
    0.06
    лини
    0.06
    /gtest
    0.06
    Activations Density 0.001%

    No Known Activations