© 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 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. 56120
    Prev
    Next
    INDEX
    Explanations

    references to multitasking and background activities

    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
    Äĥm
    -0.06
     Mission
    -0.06
    enis
    -0.06
    ADI
    -0.06
    itel
    -0.06
    á»Ļc
    -0.06
    [res
    -0.06
    atches
    -0.06
    cached
    -0.06
    iteli
    -0.06
    POSITIVE LOGITS
    ueur
    0.07
    ylie
    0.07
    oon
    0.07
    IOR
    0.06
    adh
    0.06
    alen
    0.06
    ourage
    0.06
    alu
    0.06
    WebResponse
    0.06
    ennen
    0.06
    Activations Density 0.014%

    No Known Activations