© 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. 3097
    Prev
    Next
    INDEX
    Explanations

    references to musical performances and orchestras

    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
    angler
    -0.07
    ìĩ
    -0.07
    //{{
    -0.07
    æŁĦ
    -0.07
    ilib
    -0.07
    ÅĽnie
    -0.07
    utsche
    -0.07
    DidLoad
    -0.07
    aghan
    -0.07
    æİ
    -0.07
    POSITIVE LOGITS
     band
    0.07
     Associates
    0.06
     reg
    0.06
     surrounds
    0.06
     Hi
    0.06
     +
    0.06
     Band
    0.06
    minus
    0.06
     associates
    0.06
    anj
    0.05
    Activations Density 0.021%

    No Known Activations