© 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 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. 3499
    Prev
    Next
    INDEX
    Explanations

    words related to musical themes or genres

    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
    xx
    -0.06
     exposition
    -0.06
    arkin
    -0.06
     consec
    -0.06
     camel
    -0.06
    empt
    -0.06
     cons
    -0.06
    -0.06
     kale
    -0.06
     Fel
    -0.06
    POSITIVE LOGITS
     symbol
    0.12
     symbolic
    0.11
    symbol
    0.10
     symbolism
    0.10
     Symbol
    0.10
     Ñģимвол
    0.10
     symbols
    0.10
    -symbol
    0.10
     SYMBOL
    0.09
    .symbol
    0.09
    Activations Density 0.009%

    No Known Activations