© 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. 85248
    Prev
    Next
    INDEX
    Explanations

    references to experimental group comparisons in a study

    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
    inch
    -0.07
    wie
    -0.06
     undergo
    -0.06
     [](
    -0.06
     strateg
    -0.05
    utura
    -0.05
    inz
    -0.05
    adera
    -0.05
    rière
    -0.05
    anken
    -0.05
    POSITIVE LOGITS
     toItem
    0.07
    ResultsController
    0.07
     Conway
    0.07
    ¦æĥħ
    0.07
    PFN
    0.07
    ointment
    0.07
    argins
    0.07
     [+
    0.06
    ÑĸÑĪ
    0.06
     عزÛĮز
    0.06
    Activations Density 0.022%

    No Known Activations