© 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. 126517
    Prev
    Next
    INDEX
    Explanations

    phrases related to committees or groups with specific functions or goals

    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
    soon
    -0.07
    ucu
    -0.07
    isko
    -0.07
    iegel
    -0.07
    iali
    -0.06
    kili
    -0.06
    992
    -0.06
    owo
    -0.06
    hores
    -0.06
    zag
    -0.06
    POSITIVE LOGITS
     would
    0.10
     بتÙĪاÙĨ
    0.10
    would
    0.09
    -нибÑĥдÑĮ
    0.08
     Would
    0.08
     could
    0.08
    oller
    0.08
    èĥ½å¤Ł
    0.08
     preferably
    0.07
     pueda
    0.07
    Activations Density 0.063%

    No Known Activations