© 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. 85453
    Prev
    Next
    INDEX
    Explanations

    technical references or code snippets related to programming

    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
    antal
    -0.07
     wor
    -0.06
    ÚĺÙĨ
    -0.06
    hor
    -0.06
    uide
    -0.06
    UGHT
    -0.06
    ieu
    -0.06
     Studi
    -0.06
    ongyang
    -0.06
    inf
    -0.06
    POSITIVE LOGITS
     Gesch
    0.06
    _LS
    0.06
    vvm
    0.06
    maal
    0.06
    ÑĪка
    0.06
    owy
    0.06
     vòng
    0.05
    arlo
    0.05
     мене
    0.05
     Corinth
    0.05
    Activations Density 0.001%

    No Known Activations