© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 125427
    Prev
    Next
    INDEX
    Explanations

    coding or programming elements in the text

    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
    egt
    -0.08
    vertime
    -0.07
    ÑĥÑĢÑĥ
    -0.07
    á»ĩ
    -0.07
     доÑģÑĤ
    -0.07
    empo
    -0.07
    zan
    -0.07
    ificado
    -0.07
    clipse
    -0.07
    еÑĢе
    -0.07
    POSITIVE LOGITS
     central
    0.06
    isms
    0.06
     northern
    0.05
    itt
    0.05
    iesz
    0.05
     Humph
    0.05
     éł
    0.05
     Central
    0.05
    aina
    0.05
     rice
    0.05
    Activations Density 0.000%

    No Known Activations