© 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. 119317
    Prev
    Next
    INDEX
    Explanations

    references to various versions of the Windows operating system

    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
    usc
    -0.08
    eut
    -0.07
    alars
    -0.07
    ublish
    -0.07
    unic
    -0.07
    geh
    -0.07
    -0.07
    aters
    -0.07
    ep
    -0.07
    tings
    -0.07
    POSITIVE LOGITS
    /Linux
    0.09
    rum
    0.07
    (WIN
    0.07
    -gnu
    0.07
    based
    0.07
    æĪ·
    0.07
    oren
    0.07
    çħ§
    0.07
    izzo
    0.07
    bourne
    0.07
    Activations Density 0.009%

    No Known Activations