© 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. 38643
    Prev
    Next
    INDEX
    Explanations

    statistical data and numerical patterns related to time periods or events

    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
    ilha
    -0.07
    \R
    -0.07
    inha
    -0.07
    gil
    -0.07
     dedi
    -0.06
    ản
    -0.06
    برÛĮ
    -0.06
    lej
    -0.06
    åĮ
    -0.06
    одав
    -0.06
    POSITIVE LOGITS
    iami
    0.07
    _ONLY
    0.06
    times
    0.06
    ConverterFactory
    0.06
    arak
    0.06
    upp
    0.06
     Forces
    0.06
     (<
    0.06
    only
    0.06
    ipped
    0.06
    Activations Density 0.137%

    No Known Activations