© 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. 82159
    Prev
    Next
    INDEX
    Explanations

    instances of phrases indicating beginnings and changes in action

    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
    ä½IJ
    -0.07
    pis
    -0.07
    ution
    -0.06
    سÙĩ
    -0.06
    URING
    -0.06
     ä½IJ
    -0.06
    Specifier
    -0.06
    _SITE
    -0.06
     continu
    -0.06
    é§IJ
    -0.06
    POSITIVE LOGITS
     become
    0.08
     quite
    0.07
     becoming
    0.07
     now
    0.07
    midd
    0.07
    aina
    0.07
    uggy
    0.07
    .UnitTesting
    0.06
    bec
    0.06
    ZE
    0.06
    Activations Density 0.011%

    No Known Activations