© 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. 86805
    Prev
    Next
    INDEX
    Explanations

    links to Google Analytics and related URLs

    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
    ife
    -0.07
    urum
    -0.06
    cé
    -0.06
    apel
    -0.06
    ué
    -0.06
    uru
    -0.06
     impl
    -0.06
    eut
    -0.06
    apan
    -0.05
    Alchemy
    -0.05
    POSITIVE LOGITS
     Speedway
    0.08
    ialis
    0.07
    ADIUS
    0.07
    âĦĸâĦĸ
    0.07
    Intialized
    0.07
     norge
    0.07
     Blaze
    0.07
    (*)(
    0.07
    inker
    0.07
    rial
    0.07
    Activations Density 0.009%

    No Known Activations