© 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. 117659
    Prev
    Next
    INDEX
    Explanations

    key character names and important plot points

    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
    edback
    -0.09
    serter
    -0.08
    onz
    -0.08
    ilon
    -0.07
    ILON
    -0.07
    iyon
    -0.07
    essaging
    -0.07
     ÑĤва
    -0.07
    onica
    -0.07
    iÅŁti
    -0.07
    POSITIVE LOGITS
     government
    0.06
     initially
    0.06
    ár
    0.06
    Adj
    0.05
     adj
    0.05
    Calibri
    0.05
    792
    0.05
     officially
    0.05
     resign
    0.05
     draft
    0.05
    Activations Density 0.001%

    No Known Activations