© 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. 28652
    Prev
    Next
    INDEX
    Explanations

    mathematical terms related to algorithms and optimization methods

    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
    apı
    -0.07
    rve
    -0.07
    -urlencoded
    -0.07
    ãĤ¦ãĥĪ
    -0.07
    anity
    -0.07
     Äijo
    -0.06
    /Foundation
    -0.06
    erald
    -0.06
    aoke
    -0.06
    าà¸
    -0.06
    POSITIVE LOGITS
     approach
    0.08
    -based
    0.07
     least
    0.07
     Approach
    0.07
     based
    0.06
     method
    0.06
     approaches
    0.06
    onet
    0.06
    anz
    0.06
     Variant
    0.06
    Activations Density 0.200%

    No Known Activations