© 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. 58937
    Prev
    Next
    INDEX
    Explanations

    references to waiting or processing times in a context involving queues or lines

    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
    ivre
    -0.07
    zyst
    -0.07
    ivy
    -0.07
     afore
    -0.06
    ÌĢ
    -0.06
    731
    -0.06
    éli
    -0.06
    OperationException
    -0.06
    agnosis
    -0.06
     magn
    -0.06
    POSITIVE LOGITS
    //{{
    0.07
    bz
    0.07
    áºŃm
    0.07
    rubu
    0.07
     ax
    0.06
    _Selection
    0.06
    ertino
    0.06
    ìĻĦ
    0.06
    ÑĪÑĮ
    0.06
     moi
    0.06
    Activations Density 0.000%

    No Known Activations