© 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. 69465
    Prev
    Next
    INDEX
    Explanations

    references to classes, variables, environmental factors, and transportation options

    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
    apon
    -0.08
    layarak
    -0.07
    zı
    -0.07
    .allowed
    -0.07
    imax
    -0.07
    /by
    -0.07
    лиÑĪ
    -0.07
     रहन
    -0.07
    _CHK
    -0.07
    .Keyboard
    -0.07
    POSITIVE LOGITS
    âĢ¦↵↵↵
    0.07
    ä¹ĭä¸Ģ
    0.06
    ouser
    0.06
    OfType
    0.06
    edicine
    0.06
    392
    0.06
    @Id
    0.06
    nds
    0.06
    à¸ķร
    0.06
     TBD
    0.06
    Activations Density 0.030%

    No Known Activations