© 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. 17-LLAMASCOPE-RES-131K
    6. 119822
    Prev
    Next
    INDEX
    Explanations

    words describing suitability and ideal conditions for products or solutions

    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
     gratuiti
    -0.07
    Ľi
    -0.07
    chia
    -0.07
    opsis
    -0.07
    iece
    -0.07
    æŀ
    -0.07
     Ballard
    -0.07
    kar
    -0.07
    iosper
    -0.06
    ÑĢад
    -0.06
    POSITIVE LOGITS
     for
    0.08
    ittle
    0.07
     anyone
    0.07
     especially
    0.06
     use
    0.06
    ÙĮ
    0.06
     voor
    0.06
     anytime
    0.06
    avad
    0.06
     für
    0.06
    Activations Density 0.015%

    No Known Activations