© 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. 92152
    Prev
    Next
    INDEX
    Explanations

    numerical data related to statistics and analysis

    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
    ắc
    -0.06
    даÑĤ
    -0.06
    íĴ
    -0.06
    afen
    -0.06
    esp
    -0.06
    OSH
    -0.06
     AssemblyCopyright
    -0.06
    Injected
    -0.06
    _nth
    -0.06
    Å¡tÃŃ
    -0.06
    POSITIVE LOGITS
    ura
    0.08
    509
    0.07
    é
    0.06
     surg
    0.06
    ø
    0.06
    rav
    0.06
    521
    0.06
     count
    0.06
    umpt
    0.06
    542
    0.06
    Activations Density 0.002%

    No Known Activations