© 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. 40495
    Prev
    Next
    INDEX
    Explanations

    queries pertaining to costs and installations related to flooring

    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
    retty
    -0.09
    -valu
    -0.08
    chan
    -0.07
    amburger
    -0.07
    alog
    -0.07
    ureau
    -0.07
    inkle
    -0.07
    ereotype
    -0.07
    ÏģÏĮ
    -0.06
    gressor
    -0.06
    POSITIVE LOGITS
     Merlin
    0.06
     washed
    0.06
     Christmas
    0.06
    csrf
    0.06
    Keywords
    0.06
     Sou
    0.06
     wash
    0.05
     str
    0.05
     Fit
    0.05
    ucher
    0.05
    Activations Density 0.002%

    No Known Activations