© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 14846
    Prev
    Next
    INDEX
    Explanations

    references to music, musicians, and their works

    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
     Mens
    -0.07
    asca
    -0.07
    eti
    -0.07
    WIN
    -0.06
    582
    -0.06
    iyat
    -0.06
    ODEV
    -0.06
     drummer
    -0.06
     Drum
    -0.06
    edn
    -0.06
    POSITIVE LOGITS
     rat
    0.07
     recording
    0.06
    unte
    0.06
    actory
    0.06
     toe
    0.06
    PUR
    0.06
    ulos
    0.06
     Standard
    0.06
    ophone
    0.06
    inkle
    0.06
    Activations Density 0.011%

    No Known Activations