© 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. 15-LLAMASCOPE-RES-131K
    11. 62353
    Prev
    Next
    INDEX
    Explanations

    references to mechanical or operational processes

    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
    apel
    -0.08
     publicly
    -0.06
    lav
    -0.06
    kelig
    -0.06
    SupportedContent
    -0.06
    ané
    -0.06
    alus
    -0.06
    uraa
    -0.06
     clearly
    -0.06
    anova
    -0.06
    POSITIVE LOGITS
    skins
    0.09
    .serializer
    0.08
    اÙĦات
    0.08
    Ÿ
    0.07
    ãĤ¹ãĤ¯
    0.07
    è¨
    0.07
    ãİ
    0.07
    antt
    0.07
    ÙĪÙħات
    0.07
    ,:,
    0.07
    Activations Density 0.002%

    No Known Activations