© 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. 72574
    Prev
    Next
    INDEX
    Explanations

    words related to musical elements and performers

    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
    otch
    -0.07
     compromises
    -0.07
    itchen
    -0.07
    +]
    -0.06
    è¼Ŀ
    -0.06
     Handling
    -0.06
    izmet
    -0.06
    tap
    -0.06
    igu
    -0.06
    ivo
    -0.06
    POSITIVE LOGITS
    eyh
    0.07
    éric
    0.07
    \Middleware
    0.06
    URED
    0.06
    701
    0.06
    DBG
    0.06
    Ķ
    0.06
     FRA
    0.06
    .localized
    0.06
    ifr
    0.06
    Activations Density 0.019%

    No Known Activations