© 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. 80998
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their statements or actions

    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
    ansa
    -0.07
    isol
    -0.07
    omba
    -0.06
     %{
    -0.06
    orgen
    -0.06
    itta
    -0.06
     Civilization
    -0.06
     Renderer
    -0.06
    illage
    -0.06
    ords
    -0.06
    POSITIVE LOGITS
     hass
    0.07
    æ®
    0.06
    essler
    0.06
    ono
    0.06
    aset
    0.06
     Ferry
    0.06
    830
    0.06
    kili
    0.05
    bon
    0.05
    .toolbox
    0.05
    Activations Density 0.021%

    No Known Activations