© 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. 30386
    Prev
    Next
    INDEX
    Explanations

    terms related to development and management in business contexts

    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
    anes
    -0.08
    Äįer
    -0.08
    krv
    -0.08
    .TabStop
    -0.07
    rowable
    -0.07
    orado
    -0.07
    رÛĮÙģ
    -0.07
    είÏĦε
    -0.07
    loquent
    -0.07
    okt
    -0.07
    POSITIVE LOGITS
     daily
    0.08
    iec
    0.07
     successfully
    0.07
    Was
    0.06
     weekly
    0.06
    0.06
     several
    0.06
     cas
    0.06
    TEGER
    0.06
    ô
    0.06
    Activations Density 0.027%

    No Known Activations