© 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. 125705
    Prev
    Next
    INDEX
    Explanations

    references to page numbers and publication statistics

    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
    esan
    -0.07
    sein
    -0.06
     Unt
    -0.06
    sey
    -0.06
     ÙħÙĩر
    -0.06
    allel
    -0.06
    lients
    -0.06
     Day
    -0.06
     day
    -0.05
    /tree
    -0.05
    POSITIVE LOGITS
    edores
    0.08
     fotos
    0.07
    pcf
    0.07
    agt
    0.07
    iland
    0.07
    /format
    0.07
    elic
    0.07
    iesel
    0.07
    imenti
    0.07
    ildo
    0.07
    Activations Density 0.004%

    No Known Activations