© 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. 9-LLAMASCOPE-RES-131K
    11. 96519
    Prev
    Next
    INDEX
    Explanations

    mentions of lounge or relaxation spaces

    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
    son
    -0.08
    awy
    -0.07
    fall
    -0.07
    Ñĥнок
    -0.07
    deaux
    -0.07
    ullah
    -0.07
    tra
    -0.07
    falls
    -0.07
    iego
    -0.06
    sons
    -0.06
    POSITIVE LOGITS
    ette
    0.07
    alaxy
    0.07
    iloc
    0.06
    .way
    0.06
    acyj
    0.06
    yor
    0.06
    Ð¡Ðł
    0.06
    tic
    0.06
    tility
    0.06
    TextNode
    0.06
    Activations Density 0.005%

    No Known Activations