© 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. 79746
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential or conditional outcomes

    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
    _glob
    -0.07
     داÙĪ
    -0.07
    taj
    -0.06
    ê·ľ
    -0.06
    æħĭ
    -0.06
    aleur
    -0.06
    olin
    -0.06
    æľºåħ³
    -0.06
    nameof
    -0.06
    appable
    -0.06
    POSITIVE LOGITS
     chances
    0.09
     will
    0.08
    will
    0.07
    å°±ä¼ļ
    0.07
     becomes
    0.07
    ä¼ļ
    0.07
     tends
    0.07
    ÑĨо
    0.06
     Zucker
    0.06
     tended
    0.06
    Activations Density 0.034%

    No Known Activations