© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 106218
    Prev
    Next
    INDEX
    Explanations

    the word "once" in various contexts

    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
    arge
    -0.07
    .catch
    -0.06
    oger
    -0.06
    inclusive
    -0.06
    abant
    -0.06
    444
    -0.06
    ùi
    -0.06
    ghi
    -0.06
     вз
    -0.06
     Pel
    -0.06
    POSITIVE LOGITS
     once
    0.11
    once
    0.10
     Once
    0.09
    Once
    0.08
     again
    0.08
    again
    0.08
    ä¸Ģ度
    0.07
    ä¸Ģ次
    0.07
    _ONCE
    0.07
     Again
    0.07
    Activations Density 0.016%

    No Known Activations