© 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. 54767
    Prev
    Next
    INDEX
    Explanations

    references to contemporary themes or concepts

    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
    apy
    -0.07
    Closure
    -0.07
    ifton
    -0.07
    icerca
    -0.07
    æĹ©
    -0.07
    è¿ĩåİ»
    -0.07
    phere
    -0.07
     lately
    -0.07
    amework
    -0.07
    mtree
    -0.06
    POSITIVE LOGITS
    618
    0.07
    .integration
    0.06
    /up
    0.06
    sert
    0.06
     equivalents
    0.06
    /mod
    0.06
    umph
    0.06
     Alg
    0.06
    -era
    0.06
     ÙħÛĮÙĦادÛĮ
    0.06
    Activations Density 0.004%

    No Known Activations