© 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. 129721
    Prev
    Next
    INDEX
    Explanations

    references to low-cost or low-maintenance attributes

    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
    iesz
    -0.07
    ãĥ³ãĤ¯
    -0.07
    aman
    -0.07
     meis
    -0.06
    nung
    -0.06
    inea
    -0.06
    cesso
    -0.06
    ollapse
    -0.06
    hte
    -0.06
    fea
    -0.06
    POSITIVE LOGITS
     risk
    0.08
    enstein
    0.07
     maintenance
    0.07
     footprint
    0.07
    omi
    0.07
    enton
    0.07
     cost
    0.07
     requirements
    0.07
    elay
    0.06
     consum
    0.06
    Activations Density 0.018%

    No Known Activations