© 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. 15-LLAMASCOPE-RES-131K
    11. 86705
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to music and musical acts

    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
    Solo
    -0.07
    acho
    -0.06
    ãĥ´ãĤ£
    -0.06
    /editor
    -0.06
    åķ
    -0.06
    ekil
    -0.06
    ĶĶ
    -0.06
     Solo
    -0.06
     his
    -0.06
     itemprop
    -0.05
    POSITIVE LOGITS
     themselves
    0.08
    cheid
    0.08
    _MEMBERS
    0.07
    æĪIJåijĺ
    0.07
    monds
    0.07
     thems
    0.07
    VOID
    0.07
    ramework
    0.07
     fans
    0.07
    aid
    0.07
    Activations Density 0.041%

    No Known Activations