© 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. 83652
    Prev
    Next
    INDEX
    Explanations

    specific references to music or recordings

    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
     Cruise
    -0.07
    occo
    -0.06
     Oak
    -0.06
    ccione
    -0.06
     Atl
    -0.06
    olumn
    -0.06
    ollen
    -0.06
    Äįná
    -0.06
    DAQ
    -0.06
    Atl
    -0.06
    POSITIVE LOGITS
    attles
    0.07
    ARTH
    0.07
    forman
    0.06
    lad
    0.06
    abad
    0.06
    moth
    0.06
     entire
    0.06
    ansom
    0.06
    éħ
    0.06
    ινÏĮ
    0.06
    Activations Density 0.000%

    No Known Activations