© 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. 76520
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific individual or character and their associations

    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
    _utilities
    -0.07
    562
    -0.06
    ì²
    -0.06
     dap
    -0.06
    razil
    -0.06
     geh
    -0.06
    quare
    -0.06
    λαν
    -0.06
    Äįen
    -0.06
     ëª
    -0.06
    POSITIVE LOGITS
    imonial
    0.07
     somehow
    0.07
    ahoma
    0.06
    acha
    0.06
    oment
    0.06
    imonials
    0.06
     animals
    0.06
    aco
    0.06
    inton
    0.06
     humane
    0.06
    Activations Density 0.001%

    No Known Activations