© 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 EvalsExportsinterp-engineNEWAPI 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. 28316
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "once" and its contextual variations or phrases that indicate a repetitive or significant event

    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
    ifr
    -0.07
    olik
    -0.07
    anna
    -0.06
     downright
    -0.06
    ior
    -0.06
    alker
    -0.06
    io
    -0.06
    essor
    -0.06
     Ke
    -0.06
    unami
    -0.05
    POSITIVE LOGITS
     once
    0.14
     Once
    0.12
    once
    0.11
    Once
    0.11
     einmal
    0.10
    ä¸Ģ次
    0.09
    _once
    0.09
    .Once
    0.09
     jednou
    0.09
     íķľë²Ī
    0.08
    Activations Density 0.018%

    No Known Activations