© 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. 94607
    Prev
    Next
    INDEX
    Explanations

    information related to power specifications and compatibility of USB technologies

    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
     tic
    -0.07
    bow
    -0.06
    isman
    -0.06
     cá»Ńa
    -0.06
     bearings
    -0.06
    land
    -0.06
    SMS
    -0.06
    ió
    -0.06
     zipper
    -0.06
     tablet
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.08
     Distance
    0.08
     Po
    0.07
    /power
    0.07
    abaj
    0.07
    (æ°´
    0.07
    (po
    0.07
    ÂłPS
    0.07
    #ad
    0.07
     po
    0.07
    Activations Density 0.001%

    No Known Activations