© 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. 55318
    Prev
    Next
    INDEX
    Explanations

    references to musical compositions and their creators

    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
    NYSE
    -0.07
     behind
    -0.06
    imitive
    -0.06
    åĢ«
    -0.06
    zew
    -0.06
    uiltin
    -0.06
    luv
    -0.06
     natural
    -0.06
     meilleurs
    -0.06
    èĪĪ
    -0.05
    POSITIVE LOGITS
    جÙĨ
    0.08
    semblies
    0.07
    uyá»ĩn
    0.06
    ased
    0.06
     sublicense
    0.06
     dimension
    0.06
    _pdu
    0.06
    dimension
    0.06
    Ñİк
    0.06
    год
    0.06
    Activations Density 0.004%

    No Known Activations