© 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. 130997
    Prev
    Next
    INDEX
    Explanations

    references to significant historical events and figures

    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
     recently
    -0.10
    Recently
    -0.08
     upcoming
    -0.08
     Recently
    -0.08
    recent
    -0.08
     recent
    -0.08
     forthcoming
    -0.08
     lately
    -0.08
     soon
    -0.07
    _recent
    -0.07
    POSITIVE LOGITS
     began
    0.07
    uzzi
    0.07
    bare
    0.06
     publication
    0.06
     originally
    0.06
    ramer
    0.06
     start
    0.06
     ì²ĺìĿĮ
    0.06
     first
    0.06
    ota
    0.06
    Activations Density 0.031%

    No Known Activations