© 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. 3588
    Prev
    Next
    INDEX
    Explanations

    descriptions of emotional impact in music and performance

    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
    iesen
    -0.07
    abin
    -0.06
    udget
    -0.06
     refer
    -0.06
    upo
    -0.06
    ething
    -0.06
    von
    -0.06
    anja
    -0.06
    kening
    -0.05
    emy
    -0.05
    POSITIVE LOGITS
    odel
    0.07
    립
    0.07
    ạc
    0.07
    åŃIJãģ¯
    0.07
    ìŀ¥ìĿĢ
    0.07
     Cousins
    0.07
    errat
    0.07
     Äįin
    0.07
    idir
    0.07
    åĮ
    0.06
    Activations Density 0.043%

    No Known Activations