© 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. 130246
    Prev
    Next
    INDEX
    Explanations

    references to companies providing services and their respective qualities

    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
    BuilderFactory
    -0.06
     Protected
    -0.06
     protected
    -0.06
     Stewart
    -0.06
    uzey
    -0.06
    ilha
    -0.05
    å»
    -0.05
    enville
    -0.05
     ill
    -0.05
     fall
    -0.05
    POSITIVE LOGITS
     cliente
    0.08
     combos
    0.07
    nen
    0.07
    client
    0.07
    éĽĦ
    0.07
    _recursive
    0.06
    argon
    0.06
     combo
    0.06
     ë¿IJ
    0.06
    -client
    0.06
    Activations Density 0.026%

    No Known Activations