© 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. 390
    Prev
    Next
    INDEX
    Explanations

    references to official identifiers related to social and business contexts

    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
    uja
    -0.06
    832
    -0.06
    ung
    -0.06
    ows
    -0.06
    opensource
    -0.06
    ND
    -0.06
    eki
    -0.06
    Scale
    -0.06
    vil
    -0.06
     scales
    -0.05
    POSITIVE LOGITS
     بÙĪاسطة
    0.08
     تÙĪسط
    0.08
     responsibility
    0.08
     ìĿĺíķ´
    0.08
    _Impl
    0.07
     Responsibility
    0.07
    æĿ¥æºIJ
    0.07
    çĶ±
    0.07
    ownership
    0.07
    ãĤ¤ãĥī
    0.07
    Activations Density 0.096%

    No Known Activations