© 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. 27944
    Prev
    Next
    INDEX
    Explanations

    references to cloud-based audio services

    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
    кеÑĤ
    -0.07
    ems
    -0.07
    GuidId
    -0.06
    973
    -0.06
    å¼ķãģį
    -0.06
    Ìģt
    -0.06
    rete
    -0.06
    hab
    -0.06
    èIJ½
    -0.06
     lag
    -0.06
    POSITIVE LOGITS
    plib
    0.08
    ieux
    0.07
    counts
    0.07
     Album
    0.07
    .oauth
    0.07
    /portfolio
    0.07
     Ally
    0.07
    /photos
    0.07
    iggins
    0.07
    API
    0.07
    Activations Density 0.004%

    No Known Activations