© 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. 27902
    Prev
    Next
    INDEX
    Explanations

    references to cultural contributions and community heritage

    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
    жив
    -0.09
    ãĥĨãĥ«
    -0.07
    ÑĥÑĪки
    -0.07
    Breadcrumb
    -0.06
     Podle
    -0.06
    inia
    -0.06
    Rendering
    -0.06
    erokee
    -0.06
    backend
    -0.06
    глÑı
    -0.06
    POSITIVE LOGITS
     host
    0.08
     history
    0.08
     symbolism
    0.08
    ekim
    0.07
    hosts
    0.07
    symbol
    0.07
     History
    0.07
    /history
    0.07
     histories
    0.07
     prot
    0.07
    Activations Density 0.037%

    No Known Activations