© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 117996
    Prev
    Next
    INDEX
    Explanations

    musical terms and concepts related to vocal performances

    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
    ença
    -0.07
    :both
    -0.07
    IEL
    -0.07
    зÑı
    -0.07
    iag
    -0.07
    lparr
    -0.07
    presso
    -0.07
    awy
    -0.07
    tings
    -0.07
    lore
    -0.07
    POSITIVE LOGITS
    /light
    0.06
     foil
    0.06
    bol
    0.06
    olist
    0.06
    /s
    0.06
    ıs
    0.06
     bolts
    0.06
    /lib
    0.06
     trim
    0.06
    bis
    0.06
    Activations Density 0.002%

    No Known Activations