© 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. 15832
    Prev
    Next
    INDEX
    Explanations

    references to classical music and its associated concepts

    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
    orial
    -0.10
    Ìĥ
    -0.07
    eds
    -0.07
    ekt
    -0.07
    оÑĢм
    -0.06
    ter
    -0.06
    ings
    -0.06
    oras
    -0.06
    eger
    -0.06
    tings
    -0.06
    POSITIVE LOGITS
    mente
    0.08
    -trained
    0.07
    åĪ«
    0.07
    trained
    0.07
     trained
    0.07
     же
    0.07
    PEED
    0.07
    ilian
    0.07
    ayne
    0.07
    zed
    0.07
    Activations Density 0.007%

    No Known Activations