© 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. 58584
    Prev
    Next
    INDEX
    Explanations

    references to specific literary techniques and concepts

    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
     currently
    -0.12
    currently
    -0.10
    缮åīį
    -0.10
     Currently
    -0.09
     current
    -0.09
     Recent
    -0.09
     presently
    -0.08
     recent
    -0.08
    Currently
    -0.08
    current
    -0.08
    POSITIVE LOGITS
     himself
    0.09
     wrote
    0.08
     famously
    0.07
     lifelong
    0.07
     writing
    0.07
    ारà¤ķ
    0.07
    tsky
    0.06
    .getInstance
    0.06
     privile
    0.06
     personally
    0.06
    Activations Density 0.061%

    No Known Activations