© 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. 28660
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to classification algorithms and machine learning processes

    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
    Ø´ÙĨ
    -0.08
    kü
    -0.07
    unce
    -0.07
    oyer
    -0.07
     Jame
    -0.06
    loe
    -0.06
    æĺ¯æĪij
    -0.06
    ritel
    -0.06
    ắt
    -0.06
     obou
    -0.06
    POSITIVE LOGITS
     usually
    0.09
     typically
    0.09
    usually
    0.09
     Usually
    0.08
     somehow
    0.08
     often
    0.08
     either
    0.08
    Usually
    0.08
    often
    0.07
     Either
    0.07
    Activations Density 0.033%

    No Known Activations