© 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. 86416
    Prev
    Next
    INDEX
    Explanations

    content related to travel information and tips

    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
    ÑĩеÑĢ
    -0.06
    aks
    -0.06
    uci
    -0.06
    alerts
    -0.05
    ulton
    -0.05
    quel
    -0.05
     Butt
    -0.05
    untu
    -0.05
    obar
    -0.05
    á»ijc
    -0.05
    POSITIVE LOGITS
    /ms
    0.07
    AMED
    0.07
    metatable
    0.07
    URLException
    0.07
    ŀæĢ§
    0.07
     spraying
    0.07
    usercontent
    0.06
    IDES
    0.06
    .jackson
    0.06
    UrlParser
    0.06
    Activations Density 0.004%

    No Known Activations